Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.9103. Min Act: -0.1700
Data Index: 458048 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.8478. Min Act: -0.1700
Data Index: 7698521 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.7228. Min Act: -0.1700
Data Index: 533736 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.6603. Min Act: -0.1700
Data Index: 5495251 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.6603. Min Act: -0.1700
Data Index: 1753995 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.5978. Min Act: -0.1700
Data Index: 3000595 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.4728. Min Act: -0.1700
Data Index: 1067276 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.4728. Min Act: -0.1700
Data Index: 2797577 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.4103. Min Act: -0.1700
Data Index: 3426916 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.3478. Min Act: -0.1700
Data Index: 6963288 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.3478. Min Act: -0.1700
Data Index: 2049293 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.2853. Min Act: -0.1700
Data Index: 1799669 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.2228. Min Act: -0.1700
Data Index: 6548980 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.2228. Min Act: -0.1700
Data Index: 3908692 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.1603. Min Act: -0.1700
Data Index: 6210181 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.1603. Min Act: -0.1700
Data Index: 3926945 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.0978. Min Act: -0.1700
Data Index: 3128319 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.0978. Min Act: -0.1700
Data Index: 2599171 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.0978. Min Act: -0.1700
Data Index: 3544848 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9103. Min Range: -11.9103
Max Act: 11.0978. Min Act: -0.1700
Data Index: 2228812 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19