Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5230. Min Range: -8.5230
Max Act: 8.5230. Min Act: -0.1700
Data Index: 7464141 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5230. Min Range: -8.5230
Max Act: 8.3980. Min Act: -0.1700
Data Index: 5217024 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5230. Min Range: -8.5230
Max Act: 8.2105. Min Act: -0.1700
Data Index: 2807286 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5230. Min Range: -8.5230
Max Act: 8.2105. Min Act: -0.1700
Data Index: 4111967 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.9605. Min Act: -0.1700
Data Index: 8549422 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.7730. Min Act: -0.1700
Data Index: 3688535 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.7105. Min Act: -0.1700
Data Index: 7929026 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.6793. Min Act: -0.1700
Data Index: 633626 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.6480. Min Act: -0.1700
Data Index: 7446318 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.6480. Min Act: -0.1700
Data Index: 6385864 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.5230. Min Act: -0.1700
Data Index: 7790875 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.5230. Min Act: -0.1700
Data Index: 3247374 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.5543. Min Act: -0.1700
Data Index: 7259253 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4918. Min Act: -0.1700
Data Index: 5421867 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4918. Min Act: -0.1700
Data Index: 3031944 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4918. Min Act: -0.1700
Data Index: 1317005 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4293. Min Act: -0.1700
Data Index: 6772890 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4293. Min Act: -0.1700
Data Index: 652901 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.4293. Min Act: -0.1700
Data Index: 1020257 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5230. Min Range: -8.5230
Max Act: 7.3980. Min Act: -0.1700
Data Index: 4989489 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19