Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.8722. Min Act: -0.1700
Data Index: 6123785 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.8722. Min Act: -0.1700
Data Index: 6741228 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.7472. Min Act: -0.1700
Data Index: 1971454 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.7784. Min Act: -0.1700
Data Index: 8827276 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.6222. Min Act: -0.1700
Data Index: 5180926 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.6222. Min Act: -0.1700
Data Index: 5673085 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4056227 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4972. Min Act: -0.1700
Data Index: 6717005 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4659. Min Act: -0.1700
Data Index: 3716935 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4347. Min Act: -0.1700
Data Index: 5617127 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4347. Min Act: -0.1700
Data Index: 7664187 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4034. Min Act: -0.1700
Data Index: 4085274 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.4034. Min Act: -0.1700
Data Index: 5638914 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3722. Min Act: -0.1700
Data Index: 2323311 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3722. Min Act: -0.1700
Data Index: 1060961 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3722. Min Act: -0.1700
Data Index: 6434721 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3409. Min Act: -0.1700
Data Index: 8200014 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3722. Min Act: -0.1700
Data Index: 3254966 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3409. Min Act: -0.1700
Data Index: 955191 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8722. Min Range: -5.8722
Max Act: 5.3097. Min Act: -0.1700
Data Index: 8197019 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19