Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.3553. Min Act: -0.1700
Data Index: 4151766 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.1991. Min Act: -0.1700
Data Index: 8511415 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.1678. Min Act: -0.1700
Data Index: 4764736 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.1678. Min Act: -0.1700
Data Index: 7551752 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.0741. Min Act: -0.1700
Data Index: 1880255 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.0741. Min Act: -0.1700
Data Index: 8204654 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.0428. Min Act: -0.1700
Data Index: 2859444 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.0116. Min Act: -0.1700
Data Index: 2948241 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3553. Min Range: -6.3553
Max Act: 6.0116. Min Act: -0.1700
Data Index: 7371166 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3605263 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9491. Min Act: -0.1700
Data Index: 8253530 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9178. Min Act: -0.1700
Data Index: 7208073 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5811384 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.8866. Min Act: -0.1700
Data Index: 589520 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9178. Min Act: -0.1700
Data Index: 1036426 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.9178. Min Act: -0.1700
Data Index: 336096 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.8866. Min Act: -0.1700
Data Index: 5067808 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.8866. Min Act: -0.1700
Data Index: 4334162 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.8866. Min Act: -0.1700
Data Index: 3398564 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3553. Min Range: -6.3553
Max Act: 5.8866. Min Act: -0.1700
Data Index: 1987250 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19