Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.9130. Min Act: -0.1700
Data Index: 5370110 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.7567. Min Act: -0.1700
Data Index: 4910285 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.7567. Min Act: -0.1700
Data Index: 472223 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6942. Min Act: -0.1700
Data Index: 7111977 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6630. Min Act: -0.1700
Data Index: 3665912 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6005. Min Act: -0.1700
Data Index: 8154371 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6317. Min Act: -0.1700
Data Index: 7541305 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6005. Min Act: -0.1700
Data Index: 1790322 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.6317. Min Act: -0.1700
Data Index: 1781042 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5692. Min Act: -0.1700
Data Index: 8814821 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5692. Min Act: -0.1700
Data Index: 262667 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5380. Min Act: -0.1700
Data Index: 2550593 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5067. Min Act: -0.1700
Data Index: 7361676 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5067. Min Act: -0.1700
Data Index: 5436886 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5380. Min Act: -0.1700
Data Index: 2356964 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.5067. Min Act: -0.1700
Data Index: 5444580 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.4755. Min Act: -0.1700
Data Index: 4397972 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.4442. Min Act: -0.1700
Data Index: 371427 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.4130. Min Act: -0.1700
Data Index: 4036394 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9130. Min Range: -7.9130
Max Act: 7.4130. Min Act: -0.1700
Data Index: 7867886 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19