Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.7347. Min Act: -0.1700
Data Index: 787702 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.7191. Min Act: -0.1700
Data Index: 3946670 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.6252. Min Act: -0.1700
Data Index: 5023514 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5939. Min Act: -0.1700
Data Index: 5257448 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5939. Min Act: -0.1700
Data Index: 5750568 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5626. Min Act: -0.1700
Data Index: 1507404 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5313. Min Act: -0.1700
Data Index: 982979 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5313. Min Act: -0.1700
Data Index: 2723832 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5313. Min Act: -0.1700
Data Index: 7837451 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5469. Min Act: -0.1700
Data Index: 4191432 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5156. Min Act: -0.1700
Data Index: 302296 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5156. Min Act: -0.1700
Data Index: 3774154 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5156. Min Act: -0.1700
Data Index: 164319 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5156. Min Act: -0.1700
Data Index: 8783520 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5156. Min Act: -0.1700
Data Index: 3230009 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.5000. Min Act: -0.1700
Data Index: 255514 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.4843. Min Act: -0.1700
Data Index: 2111184 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.4843. Min Act: -0.1700
Data Index: 1488234 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.4686. Min Act: -0.1700
Data Index: 5297382 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7347. Min Range: -3.7347
Max Act: 3.4686. Min Act: -0.1700
Data Index: 2209053 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19