Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2152. Min Range: -9.2152
Max Act: 9.2152. Min Act: -0.1700
Data Index: 6945368 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2152. Min Range: -9.2152
Max Act: 9.0902. Min Act: -0.1700
Data Index: 5619038 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2152. Min Range: -9.2152
Max Act: 9.0277. Min Act: -0.1700
Data Index: 400250 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2152. Min Range: -9.2152
Max Act: 9.0277. Min Act: -0.1700
Data Index: 7002321 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.9652. Min Act: -0.1700
Data Index: 8220445 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.9027. Min Act: -0.1700
Data Index: 6619195 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.9027. Min Act: -0.1700
Data Index: 3481501 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.9027. Min Act: -0.1700
Data Index: 4286083 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.9027. Min Act: -0.1700
Data Index: 4881954 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.8402. Min Act: -0.1700
Data Index: 3028178 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.8402. Min Act: -0.1700
Data Index: 2977360 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.7777. Min Act: -0.1700
Data Index: 7606351 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.7777. Min Act: -0.1700
Data Index: 3305773 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.7152. Min Act: -0.1700
Data Index: 2930385 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.7152. Min Act: -0.1700
Data Index: 381307 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.6527. Min Act: -0.1700
Data Index: 3583872 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.5902. Min Act: -0.1700
Data Index: 6808443 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.5902. Min Act: -0.1700
Data Index: 1578669 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.5902. Min Act: -0.1700
Data Index: 7059076 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2152. Min Range: -9.2152
Max Act: 8.5902. Min Act: -0.1700
Data Index: 684977 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19