Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1979 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.6717. Min Act: -0.1700
Data Index: 786708 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2090155 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.6092. Min Act: -0.1700
Data Index: 1780166 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.5780. Min Act: -0.1700
Data Index: 3697937 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.5467. Min Act: -0.1700
Data Index: 5103562 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.4842. Min Act: -0.1700
Data Index: 1309822 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.4217. Min Act: -0.1700
Data Index: 158096 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.3905. Min Act: -0.1700
Data Index: 3964342 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.4217. Min Act: -0.1700
Data Index: 5679175 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.4217. Min Act: -0.1700
Data Index: 8092424 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.3592. Min Act: -0.1700
Data Index: 563682 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.3280. Min Act: -0.1700
Data Index: 7977504 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2967. Min Act: -0.1700
Data Index: 7974233 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.3280. Min Act: -0.1700
Data Index: 2265787 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.3280. Min Act: -0.1700
Data Index: 5255270 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2967. Min Act: -0.1700
Data Index: 4544748 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2967. Min Act: -0.1700
Data Index: 3714137 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2967. Min Act: -0.1700
Data Index: 8511286 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2967. Min Act: -0.1700
Data Index: 414192 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6717. Min Range: -4.6717
Max Act: 4.2655. Min Act: -0.1700
Data Index: 2572605 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19