Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 501 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.8379. Min Act: -0.1700
Data Index: 8243781 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.5879. Min Act: -0.1700
Data Index: 1440869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.4004. Min Act: -0.1700
Data Index: 7394021 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.1504. Min Act: -0.1700
Data Index: 3726969 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 3228037 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.9004. Min Act: -0.1700
Data Index: 6967917 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.9629. Min Act: -0.1700
Data Index: 1391717 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.6504. Min Act: -0.1700
Data Index: 2924493 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 8052089 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 7552107 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1698
Data Index: 2295231 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7129. Min Act: -0.1700
Data Index: 3269514 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7129. Min Act: -0.1700
Data Index: 6416631 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 6341686 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7129. Min Act: -0.1700
Data Index: 1625650 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 7696355 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.6504. Min Act: -0.1700
Data Index: 4288050 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.6504. Min Act: -0.1700
Data Index: 8305686 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.5879. Min Act: -0.1700
Data Index: 1730894 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.5254. Min Act: -0.1693
Data Index: 8173051 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19