Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1513 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.4375. Min Act: -0.1700
Data Index: 1089036 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.3125. Min Act: -0.1700
Data Index: 2308290 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.3125. Min Act: -0.1700
Data Index: 2006555 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.1875. Min Act: -0.1700
Data Index: 1110068 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.2500. Min Act: -0.1700
Data Index: 7321747 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0625. Min Act: -0.1700
Data Index: 6194401 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.1250. Min Act: -0.1700
Data Index: 4833288 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.1250. Min Act: -0.1700
Data Index: 6993421 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0313. Min Act: -0.1700
Data Index: 8646773 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0313. Min Act: -0.1700
Data Index: 822201 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 3386301 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 5664913 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 3254948 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 3989410 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 5161096 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0313. Min Act: -0.1700
Data Index: 2068936 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4375. Min Range: -8.4375
Max Act: 8.0000. Min Act: -0.1700
Data Index: 6656037 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4375. Min Range: -8.4375
Max Act: 7.9688. Min Act: -0.1700
Data Index: 5447752 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4375. Min Range: -8.4375
Max Act: 7.9688. Min Act: -0.1700
Data Index: 1333767 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4375. Min Range: -8.4375
Max Act: 7.9688. Min Act: -0.1700
Data Index: 3959379 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19