Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.5315. Min Act: -0.1700
Data Index: 1688605 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.5002. Min Act: -0.1700
Data Index: 4847129 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.0627. Min Act: -0.1700
Data Index: 4375561 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.0627. Min Act: -0.1700
Data Index: 358189 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.0627. Min Act: -0.1700
Data Index: 481745 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5315. Min Range: -7.5315
Max Act: 7.0002. Min Act: -0.1700
Data Index: 3083832 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.9065. Min Act: -0.1700
Data Index: 5370745 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.9377. Min Act: -0.1700
Data Index: 3418841 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7815. Min Act: -0.1700
Data Index: 5163942 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7815. Min Act: -0.1700
Data Index: 8369436 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.8127. Min Act: -0.1700
Data Index: 2809725 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.8440. Min Act: -0.1700
Data Index: 2252464 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7502. Min Act: -0.1700
Data Index: 7057990 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7190. Min Act: -0.1700
Data Index: 2582538 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7502. Min Act: -0.1700
Data Index: 6792756 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.7190. Min Act: -0.1700
Data Index: 398615 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.6877. Min Act: -0.1700
Data Index: 768274 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.6877. Min Act: -0.1700
Data Index: 825085 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.6565. Min Act: -0.1700
Data Index: 2324691 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5315. Min Range: -7.5315
Max Act: 6.6252. Min Act: -0.1700
Data Index: 4883861 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19