Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3565. Min Range: -5.3565
Max Act: 5.3565. Min Act: -0.1700
Data Index: 3201577 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3565. Min Range: -5.3565
Max Act: 5.1065. Min Act: -0.1700
Data Index: 6191577 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3565. Min Range: -5.3565
Max Act: 5.0752. Min Act: -0.1700
Data Index: 4159812 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3565. Min Range: -5.3565
Max Act: 5.0440. Min Act: -0.1700
Data Index: 1095471 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3565. Min Range: -5.3565
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1768843 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9815. Min Act: -0.1700
Data Index: 2046290 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9815. Min Act: -0.1700
Data Index: 7125364 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9502. Min Act: -0.1700
Data Index: 3347750 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9815. Min Act: -0.1700
Data Index: 3104368 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9190. Min Act: -0.1700
Data Index: 8306389 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9815. Min Act: -0.1700
Data Index: 2373866 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9502. Min Act: -0.1700
Data Index: 3885641 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.9502. Min Act: -0.1700
Data Index: 2912153 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8877. Min Act: -0.1700
Data Index: 4260124 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8877. Min Act: -0.1700
Data Index: 7799285 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8565. Min Act: -0.1700
Data Index: 2046300 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8252. Min Act: -0.1700
Data Index: 5891598 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8565. Min Act: -0.1700
Data Index: 2046307 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8252. Min Act: -0.1700
Data Index: 6717329 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3565. Min Range: -5.3565
Max Act: 4.8252. Min Act: -0.1700
Data Index: 5196196 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19