Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.5520. Min Act: -0.1700
Data Index: 4416822 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.3957. Min Act: -0.1700
Data Index: 82714 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.2707. Min Act: -0.1700
Data Index: 52347 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.1770. Min Act: -0.1700
Data Index: 8397329 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.1457. Min Act: -0.1700
Data Index: 149543 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.1457. Min Act: -0.1700
Data Index: 5507523 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.0832. Min Act: -0.1700
Data Index: 1347180 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.0832. Min Act: -0.1700
Data Index: 2960132 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.0832. Min Act: -0.1700
Data Index: 4390443 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5520. Min Range: -6.5520
Max Act: 6.0207. Min Act: -0.1700
Data Index: 4624201 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.9582. Min Act: -0.1700
Data Index: 2011309 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.9270. Min Act: -0.1700
Data Index: 3256940 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.9582. Min Act: -0.1700
Data Index: 7735440 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.9270. Min Act: -0.1700
Data Index: 969424 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.9270. Min Act: -0.1700
Data Index: 7057535 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.8645. Min Act: -0.1700
Data Index: 6163042 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.8645. Min Act: -0.1700
Data Index: 7048788 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.8645. Min Act: -0.1700
Data Index: 1646078 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.8332. Min Act: -0.1700
Data Index: 8055160 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5520. Min Range: -6.5520
Max Act: 5.7707. Min Act: -0.1700
Data Index: 6833929 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19