Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 13.1879. Min Range: -13.1879
Max Act: 13.1254. Min Act: -0.1700
Data Index: 2866283 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1879. Min Range: -13.1879
Max Act: 13.1254. Min Act: -0.1700
Data Index: 4326261 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1879. Min Range: -13.1879
Max Act: 13.1879. Min Act: -0.1700
Data Index: 3814620 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1879. Min Range: -13.1879
Max Act: 13.1254. Min Act: -0.1700
Data Index: 350733 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.8754. Min Act: -0.1700
Data Index: 3735991 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.7504. Min Act: -0.1700
Data Index: 5228334 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.5004. Min Act: -0.1700
Data Index: 3444074 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.5004. Min Act: -0.1700
Data Index: 8769616 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.5629. Min Act: -0.1700
Data Index: 66291 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.3754. Min Act: -0.1700
Data Index: 6441506 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.2504. Min Act: -0.1700
Data Index: 1985501 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.3754. Min Act: -0.1700
Data Index: 5842495 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.2504. Min Act: -0.1700
Data Index: 6111013 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.1254. Min Act: -0.1700
Data Index: 4291089 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.1254. Min Act: -0.1700
Data Index: 2900463 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.1254. Min Act: -0.1700
Data Index: 2102123 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.0004. Min Act: -0.1700
Data Index: 2209311 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.0629. Min Act: -0.1700
Data Index: 998926 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1879. Min Range: -13.1879
Max Act: 12.0629. Min Act: -0.1700
Data Index: 5618440 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1879. Min Range: -13.1879
Max Act: 11.9379. Min Act: -0.1700
Data Index: 3885090 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19