Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0141. Min Range: -7.0141
Max Act: 7.0141. Min Act: -0.1700
Data Index: 3100654 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0141. Min Range: -7.0141
Max Act: 7.0141. Min Act: -0.1700
Data Index: 6150473 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.9828. Min Act: -0.1700
Data Index: 3710596 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.8891. Min Act: -0.1700
Data Index: 354087 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.8266. Min Act: -0.1700
Data Index: 4007540 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.8266. Min Act: -0.1700
Data Index: 3506488 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.7953. Min Act: -0.1700
Data Index: 4526811 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.7016. Min Act: -0.1700
Data Index: 2122280 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.7016. Min Act: -0.1700
Data Index: 6923308 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.5766. Min Act: -0.1700
Data Index: 4665125 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.6078. Min Act: -0.1700
Data Index: 2868382 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.6078. Min Act: -0.1700
Data Index: 3478897 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.6391. Min Act: -0.1700
Data Index: 1393989 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.5453. Min Act: -0.1700
Data Index: 1724824 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.5141. Min Act: -0.1700
Data Index: 982010 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.5141. Min Act: -0.1700
Data Index: 1202834 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.4516. Min Act: -0.1700
Data Index: 913918 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.4828. Min Act: -0.1700
Data Index: 31408 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.4828. Min Act: -0.1700
Data Index: 537490 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0141. Min Range: -7.0141
Max Act: 6.3891. Min Act: -0.1700
Data Index: 4091770 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19