Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0129. Min Range: -7.0129
Max Act: 7.0129. Min Act: -0.1700
Data Index: 3922022 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.7316. Min Act: -0.1700
Data Index: 4300324 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.6379. Min Act: -0.1700
Data Index: 7924801 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.6066. Min Act: -0.1700
Data Index: 3922028 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.5441. Min Act: -0.1700
Data Index: 419392 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.5441. Min Act: -0.1700
Data Index: 7812796 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.4816. Min Act: -0.1700
Data Index: 2380935 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.4504. Min Act: -0.1700
Data Index: 8104510 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.4504. Min Act: -0.1700
Data Index: 2380942 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3879. Min Act: -0.1700
Data Index: 4300311 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 900780 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3879. Min Act: -0.1700
Data Index: 3292762 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4300318 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4300319 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 2100985 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 6338969 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4300322 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5792623 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.3254. Min Act: -0.1700
Data Index: 1754590 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0129. Min Range: -7.0129
Max Act: 6.2941. Min Act: -0.1700
Data Index: 1551472 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19