Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5081 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1498. Min Range: -14.1498
Max Act: 14.1498. Min Act: -0.1700
Data Index: 3624842 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1498. Min Range: -14.1498
Max Act: 14.0248. Min Act: -0.1700
Data Index: 639474 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.8998. Min Act: -0.1700
Data Index: 7424451 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.8373. Min Act: -0.1700
Data Index: 2905944 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.7748. Min Act: -0.1700
Data Index: 8061444 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.6498. Min Act: -0.1700
Data Index: 8208031 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.7123. Min Act: -0.1700
Data Index: 537807 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.7123. Min Act: -0.1700
Data Index: 3303695 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.7123. Min Act: -0.1700
Data Index: 2014823 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.5873. Min Act: -0.1700
Data Index: 2004595 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.5248. Min Act: -0.1700
Data Index: 4547353 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.4623. Min Act: -0.1700
Data Index: 4817160 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.4623. Min Act: -0.1700
Data Index: 1588613 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.4623. Min Act: -0.1700
Data Index: 6959448 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3998. Min Act: -0.1700
Data Index: 2830569 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3373. Min Act: -0.1700
Data Index: 2057734 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3998. Min Act: -0.1700
Data Index: 1539622 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3998. Min Act: -0.1700
Data Index: 5943516 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3998. Min Act: -0.1700
Data Index: 5127532 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1498. Min Range: -14.1498
Max Act: 13.3373. Min Act: -0.1700
Data Index: 263957 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19