Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.1057. Min Range: -12.1057
Max Act: 12.1057. Min Act: -0.1700
Data Index: 4460260 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.9182. Min Act: -0.1700
Data Index: 4502711 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.6057. Min Act: -0.1700
Data Index: 3706355 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.4807. Min Act: -0.1700
Data Index: 1738452 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2932. Min Act: -0.1700
Data Index: 7673516 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.3557. Min Act: -0.1700
Data Index: 7387236 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.3557. Min Act: -0.1700
Data Index: 2555251 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2932. Min Act: -0.1700
Data Index: 5405695 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2932. Min Act: -0.1700
Data Index: 4460261 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 7133276 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 2373151 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 8572047 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 723186 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 6690209 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 3761918 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 4269124 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 4075671 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.2307. Min Act: -0.1700
Data Index: 4754298 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.1682. Min Act: -0.1700
Data Index: 3715663 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1057. Min Range: -12.1057
Max Act: 11.1682. Min Act: -0.1700
Data Index: 4754284 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19