Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.7479. Min Act: -0.1700
Data Index: 7617215 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.5292. Min Act: -0.1700
Data Index: 6784432 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.4042. Min Act: -0.1700
Data Index: 6973678 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.3729. Min Act: -0.1700
Data Index: 2181666 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.3417. Min Act: -0.1700
Data Index: 2166244 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.3104. Min Act: -0.1700
Data Index: 295814 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.3104. Min Act: -0.1700
Data Index: 5388854 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2792. Min Act: -0.1700
Data Index: 4876957 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2792. Min Act: -0.1700
Data Index: 124293 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2792. Min Act: -0.1700
Data Index: 5307333 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 3506367 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 8756834 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 5170707 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2167. Min Act: -0.1700
Data Index: 7900234 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.2167. Min Act: -0.1700
Data Index: 3361947 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.1542. Min Act: -0.1700
Data Index: 3910039 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.1542. Min Act: -0.1700
Data Index: 6421234 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.1542. Min Act: -0.1700
Data Index: 8504577 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.1229. Min Act: -0.1700
Data Index: 592958 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7479. Min Range: -6.7479
Max Act: 6.1229. Min Act: -0.1700
Data Index: 5398834 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19