Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0428. Min Range: -5.0428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 7613571 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0428. Min Range: -5.0428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 7880769 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0428. Min Range: -5.0428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 5765028 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0428. Min Range: -5.0428
Max Act: 5.0116. Min Act: -0.1700
Data Index: 7132546 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.9803. Min Act: -0.1700
Data Index: 2165799 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.9491. Min Act: -0.1700
Data Index: 7111689 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.9491. Min Act: -0.1700
Data Index: 8495954 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.9178. Min Act: -0.1700
Data Index: 5279830 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.9178. Min Act: -0.1700
Data Index: 6130606 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 2071063 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 2717219 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 518749 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 4643504 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 987835 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 3724664 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 272083 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 5648518 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1624912 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8241. Min Act: -0.1700
Data Index: 6330925 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0428. Min Range: -5.0428
Max Act: 4.8241. Min Act: -0.1700
Data Index: 1280824 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19