Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.9818. Min Act: -0.1700
Data Index: 3346209 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.9343. Min Act: -0.1700
Data Index: 8643911 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.8550. Min Act: -0.1700
Data Index: 4499866 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.8073. Min Act: -0.1700
Data Index: 57084 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7914. Min Act: -0.1700
Data Index: 3887442 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7435. Min Act: -0.1700
Data Index: 5057034 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7595. Min Act: -0.1700
Data Index: 3083421 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7595. Min Act: -0.1700
Data Index: 1967997 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7435. Min Act: -0.1700
Data Index: 4010929 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7116. Min Act: -0.1700
Data Index: 6839159 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7116. Min Act: -0.1700
Data Index: 4221794 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7276. Min Act: -0.1700
Data Index: 8469788 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7276. Min Act: -0.1700
Data Index: 3930293 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7116. Min Act: -0.1700
Data Index: 6003610 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.7116. Min Act: -0.1700
Data Index: 3921224 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.6956. Min Act: -0.1700
Data Index: 1151455 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.6956. Min Act: -0.1700
Data Index: 4839916 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.6956. Min Act: -0.1700
Data Index: 2899415 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.6956. Min Act: -0.1700
Data Index: 5700198 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9818. Min Range: -2.9818
Max Act: 2.6796. Min Act: -0.1700
Data Index: 2177965 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19