Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.9288. Min Act: -0.1700
Data Index: 581378 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.7725. Min Act: -0.1700
Data Index: 6679621 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.6788. Min Act: -0.1700
Data Index: 6714673 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.6788. Min Act: -0.1700
Data Index: 5460641 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5850. Min Act: -0.1700
Data Index: 6686638 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.6163. Min Act: -0.1700
Data Index: 581367 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5538. Min Act: -0.1700
Data Index: 5993622 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5538. Min Act: -0.1700
Data Index: 581373 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5538. Min Act: -0.1700
Data Index: 3140795 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5538. Min Act: -0.1700
Data Index: 7991678 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5538. Min Act: -0.1700
Data Index: 581366 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5225. Min Act: -0.1700
Data Index: 6633162 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5225. Min Act: -0.1700
Data Index: 581374 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.5225. Min Act: -0.1700
Data Index: 6910496 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4913. Min Act: -0.1700
Data Index: 7495228 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4600. Min Act: -0.1700
Data Index: 4456247 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4913. Min Act: -0.1700
Data Index: 581364 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4913. Min Act: -0.1700
Data Index: 4052038 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4913. Min Act: -0.1700
Data Index: 7956653 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9288. Min Range: -7.9288
Max Act: 7.4600. Min Act: -0.1700
Data Index: 2635678 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19