Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.6004. Min Act: -0.1700
Data Index: 6355852 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5567. Min Act: -0.1649
Data Index: 8666531 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5567. Min Act: -0.1700
Data Index: 506799 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5392. Min Act: -0.1700
Data Index: 100000 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5479. Min Act: -0.1700
Data Index: 7465435 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5392. Min Act: -0.1700
Data Index: 2943607 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5392. Min Act: -0.1699
Data Index: 7275033 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5304. Min Act: -0.1700
Data Index: 8141310 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5304. Min Act: -0.1700
Data Index: 6153918 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5216. Min Act: -0.1700
Data Index: 610934 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1541
Data Index: 5474818 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5216. Min Act: -0.1695
Data Index: 932514 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5216. Min Act: -0.1534
Data Index: 6525119 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5216. Min Act: -0.1695
Data Index: 1405270 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1699
Data Index: 6525097 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1700
Data Index: 5889544 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1686
Data Index: 8097814 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1680
Data Index: 610943 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1700
Data Index: 6242649 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6004. Min Range: -1.6004
Max Act: 1.5041. Min Act: -0.1698
Data Index: 1372083 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19