Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5281 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1498. Min Range: -11.1498
Max Act: 11.1498. Min Act: -0.1700
Data Index: 2938435 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.2748. Min Act: -0.1700
Data Index: 7699130 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.2123. Min Act: -0.1700
Data Index: 2838572 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.2748. Min Act: -0.1700
Data Index: 2652235 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.1498. Min Act: -0.1700
Data Index: 4051228 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.0873. Min Act: -0.1700
Data Index: 3685121 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.0248. Min Act: -0.1700
Data Index: 2880500 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1498. Min Range: -11.1498
Max Act: 10.0248. Min Act: -0.1700
Data Index: 2384471 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.8998. Min Act: -0.1700
Data Index: 6952312 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.8373. Min Act: -0.1700
Data Index: 7796217 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.8373. Min Act: -0.1698
Data Index: 2872713 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.8373. Min Act: -0.1700
Data Index: 3793938 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7748. Min Act: -0.1700
Data Index: 5308359 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7748. Min Act: -0.1700
Data Index: 1984547 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7748. Min Act: -0.1700
Data Index: 305564 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7748. Min Act: -0.1700
Data Index: 1509982 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7123. Min Act: -0.1700
Data Index: 7261311 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.7123. Min Act: -0.1700
Data Index: 6709200 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.6498. Min Act: -0.1700
Data Index: 7491189 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1498. Min Range: -11.1498
Max Act: 9.6498. Min Act: -0.1700
Data Index: 3135724 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19