Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.3966. Min Act: -0.1700
Data Index: 1974041 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.3654. Min Act: -0.1700
Data Index: 4049451 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.3029. Min Act: -0.1700
Data Index: 4360963 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.3029. Min Act: -0.1700
Data Index: 1178527 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2716. Min Act: -0.1700
Data Index: 6035335 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2716. Min Act: -0.1700
Data Index: 3562771 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2716. Min Act: -0.1700
Data Index: 2498043 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2716. Min Act: -0.1700
Data Index: 2443835 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2091. Min Act: -0.1700
Data Index: 4456134 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.2091. Min Act: -0.1700
Data Index: 4547996 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1779. Min Act: -0.1700
Data Index: 7990672 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1779. Min Act: -0.1700
Data Index: 344666 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1779. Min Act: -0.1700
Data Index: 646693 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1779. Min Act: -0.1700
Data Index: 6151371 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 1944967 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 4295941 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1154. Min Act: -0.1700
Data Index: 2561729 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.1154. Min Act: -0.1700
Data Index: 3521468 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.0841. Min Act: -0.1700
Data Index: 5215678 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3966. Min Range: -5.3966
Max Act: 5.0841. Min Act: -0.1700
Data Index: 4112967 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19