Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.2347. Min Range: -13.2347
Max Act: 13.2347. Min Act: -0.1700
Data Index: 2636360 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.6097. Min Act: -0.1700
Data Index: 2318257 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.5472. Min Act: -0.1700
Data Index: 8374780 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.4847. Min Act: -0.1700
Data Index: 7389436 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.2347. Min Act: -0.1700
Data Index: 5961183 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.1097. Min Act: -0.1700
Data Index: 6936802 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.2347. Min Range: -13.2347
Max Act: 12.1097. Min Act: -0.1700
Data Index: 6109688 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.9222. Min Act: -0.1700
Data Index: 8185357 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.9222. Min Act: -0.1700
Data Index: 2123854 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.9222. Min Act: -0.1700
Data Index: 8144660 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.8597. Min Act: -0.1700
Data Index: 1874005 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7347. Min Act: -0.1700
Data Index: 2010207 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7972. Min Act: -0.1700
Data Index: 6369768 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7347. Min Act: -0.1700
Data Index: 2167725 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7347. Min Act: -0.1700
Data Index: 1443289 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7347. Min Act: -0.1700
Data Index: 862422 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.7347. Min Act: -0.1700
Data Index: 5091146 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.6722. Min Act: -0.1700
Data Index: 8523815 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.6722. Min Act: -0.1695
Data Index: 7761076 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.2347. Min Range: -13.2347
Max Act: 11.6722. Min Act: -0.1700
Data Index: 2278388 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19