Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2455. Min Range: -6.2455
Max Act: 6.2455. Min Act: -0.1700
Data Index: 2444766 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.8705. Min Act: -0.1700
Data Index: 5575957 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.7455. Min Act: -0.1700
Data Index: 8207509 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.6205. Min Act: -0.1700
Data Index: 944515 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.6517. Min Act: -0.1700
Data Index: 7864525 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.5267. Min Act: -0.1700
Data Index: 3582795 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.5580. Min Act: -0.1700
Data Index: 7994987 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4955. Min Act: -0.1700
Data Index: 4226344 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4955. Min Act: -0.1700
Data Index: 1493781 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4642. Min Act: -0.1700
Data Index: 4694668 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4642. Min Act: -0.1700
Data Index: 4154861 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4330. Min Act: -0.1700
Data Index: 1699778 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4017. Min Act: -0.1700
Data Index: 4517109 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4017. Min Act: -0.1700
Data Index: 2655437 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4017. Min Act: -0.1700
Data Index: 6868070 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.4017. Min Act: -0.1700
Data Index: 871407 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.3705. Min Act: -0.1700
Data Index: 1813078 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.3705. Min Act: -0.1700
Data Index: 2780484 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.3392. Min Act: -0.1700
Data Index: 3534255 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2455. Min Range: -6.2455
Max Act: 5.3080. Min Act: -0.1700
Data Index: 1683148 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19