Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.5870. Min Act: -0.1700
Data Index: 686424 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.5870. Min Act: -0.1700
Data Index: 2196545 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.4307. Min Act: -0.1700
Data Index: 6376428 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3682. Min Act: -0.1700
Data Index: 7783716 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3370. Min Act: -0.1700
Data Index: 1080087 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3370. Min Act: -0.1700
Data Index: 6376439 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3057. Min Act: -0.1700
Data Index: 6376435 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3057. Min Act: -0.1700
Data Index: 7783717 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3057. Min Act: -0.1700
Data Index: 2732612 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2745. Min Act: -0.1700
Data Index: 1989371 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4706845 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3148921 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2432. Min Act: -0.1700
Data Index: 5367212 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3872095 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2745. Min Act: -0.1700
Data Index: 6976391 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2120. Min Act: -0.1700
Data Index: 5289201 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2120. Min Act: -0.1700
Data Index: 3466198 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2120. Min Act: -0.1700
Data Index: 6017159 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2120. Min Act: -0.1700
Data Index: 6376426 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5870. Min Range: -5.5870
Max Act: 5.2120. Min Act: -0.1700
Data Index: 686425 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19