Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.3431. Min Act: -0.1700
Data Index: 7771524 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2806. Min Act: -0.1700
Data Index: 41290 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 3276666 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2493. Min Act: -0.1700
Data Index: 2036495 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 3569814 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 1060925 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 999574 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 6323110 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.2181. Min Act: -0.1700
Data Index: 1678895 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1868. Min Act: -0.1700
Data Index: 7703337 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1868. Min Act: -0.1700
Data Index: 1166182 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1868. Min Act: -0.1700
Data Index: 1338977 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1556. Min Act: -0.1700
Data Index: 819017 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1556. Min Act: -0.1700
Data Index: 8795421 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1556. Min Act: -0.1700
Data Index: 134427 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1556. Min Act: -0.1700
Data Index: 3267711 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1556. Min Act: -0.1700
Data Index: 5891039 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1243. Min Act: -0.1700
Data Index: 101977 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1243. Min Act: -0.1700
Data Index: 2174272 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3431. Min Range: -6.3431
Max Act: 6.1243. Min Act: -0.1700
Data Index: 2363808 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19