Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1390. Min Range: -6.1390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 3192507 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1390. Min Range: -6.1390
Max Act: 6.0765. Min Act: -0.1700
Data Index: 1772258 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.9828. Min Act: -0.1700
Data Index: 5068066 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8578. Min Act: -0.1700
Data Index: 6374952 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8890. Min Act: -0.1700
Data Index: 4410472 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 8634508 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2086222 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7640. Min Act: -0.1700
Data Index: 2783808 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7640. Min Act: -0.1700
Data Index: 4241208 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7640. Min Act: -0.1700
Data Index: 3177640 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 7843459 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7640. Min Act: -0.1700
Data Index: 8625917 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 1626105 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 6760351 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 8710093 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 1660783 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 6554661 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7328. Min Act: -0.1700
Data Index: 2919515 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.6703. Min Act: -0.1700
Data Index: 3225609 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7015. Min Act: -0.1700
Data Index: 1812888 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19