Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.6106. Min Act: -0.1700
Data Index: 85298 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.4230. Min Act: -0.1700
Data Index: 3587750 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3833392 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2355. Min Act: -0.1700
Data Index: 8525373 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2355. Min Act: -0.1700
Data Index: 911672 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3913588 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2043. Min Act: -0.1700
Data Index: 3193506 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2043. Min Act: -0.1700
Data Index: 2755664 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.2043. Min Act: -0.1700
Data Index: 8493331 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1730. Min Act: -0.1700
Data Index: 3193504 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1418. Min Act: -0.1700
Data Index: 3288086 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1105. Min Act: -0.1700
Data Index: 6026987 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1105. Min Act: -0.1700
Data Index: 5529834 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1105. Min Act: -0.1700
Data Index: 8038494 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1105. Min Act: -0.1700
Data Index: 6421975 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.0793. Min Act: -0.1700
Data Index: 3200053 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.1105. Min Act: -0.1700
Data Index: 7974599 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.0793. Min Act: -0.1700
Data Index: 3097907 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.0793. Min Act: -0.1700
Data Index: 3244787 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6106. Min Range: -4.6106
Max Act: 4.0793. Min Act: -0.1700
Data Index: 5078104 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19