Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.9667. Min Act: -0.1700
Data Index: 8317084 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.3417. Min Act: -0.1700
Data Index: 7017117 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.2792. Min Act: -0.1700
Data Index: 1154601 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.2167. Min Act: -0.1700
Data Index: 6088606 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.1542. Min Act: -0.1700
Data Index: 1424503 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.0292. Min Act: -0.1700
Data Index: 3268509 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.0292. Min Act: -0.1700
Data Index: 6880824 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9667. Min Range: -10.9667
Max Act: 10.0292. Min Act: -0.1700
Data Index: 3414084 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.9667. Min Act: -0.1700
Data Index: 8787160 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.9667. Min Act: -0.1700
Data Index: 1381643 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.8417. Min Act: -0.1700
Data Index: 3751010 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.7792. Min Act: -0.1700
Data Index: 5455707 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.7167. Min Act: -0.1700
Data Index: 7677733 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.7792. Min Act: -0.1700
Data Index: 4892508 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.7167. Min Act: -0.1700
Data Index: 3010289 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.6542. Min Act: -0.1700
Data Index: 2345637 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.6542. Min Act: -0.1700
Data Index: 6177505 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.6542. Min Act: -0.1700
Data Index: 4503506 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.6542. Min Act: -0.1700
Data Index: 2755700 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9667. Min Range: -10.9667
Max Act: 9.5917. Min Act: -0.1700
Data Index: 7704202 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19