Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 722 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.9481. Min Act: -0.1700
Data Index: 551869 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.9322. Min Act: -0.1700
Data Index: 8405544 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.9005. Min Act: -0.1700
Data Index: 7045713 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8529. Min Act: -0.1700
Data Index: 3662672 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8688. Min Act: -0.1700
Data Index: 1590896 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8529. Min Act: -0.1700
Data Index: 2548135 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8370. Min Act: -0.1700
Data Index: 5993953 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8370. Min Act: -0.1700
Data Index: 7414697 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8211. Min Act: -0.1700
Data Index: 2727375 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8052. Min Act: -0.1700
Data Index: 1481940 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8052. Min Act: -0.1700
Data Index: 4120273 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.8211. Min Act: -0.1700
Data Index: 6142184 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 7538920 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7414. Min Act: -0.1700
Data Index: 7438999 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 5056895 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 4455556 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7414. Min Act: -0.1700
Data Index: 2152294 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 2749869 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 6572770 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9481. Min Range: -2.9481
Max Act: 2.7574. Min Act: -0.1700
Data Index: 860130 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19