Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.5678. Min Act: -0.1700
Data Index: 348736 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.5053. Min Act: -0.1700
Data Index: 5682265 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.4115. Min Act: -0.1700
Data Index: 643038 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.3490. Min Act: -0.1700
Data Index: 7993157 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.3490. Min Act: -0.1700
Data Index: 7905357 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.3178. Min Act: -0.1700
Data Index: 1879118 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.2553. Min Act: -0.1700
Data Index: 5138295 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.2865. Min Act: -0.1700
Data Index: 6685703 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.2553. Min Act: -0.1700
Data Index: 743986 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.2553. Min Act: -0.1700
Data Index: 3527801 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.1615. Min Act: -0.1700
Data Index: 412466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.1615. Min Act: -0.1700
Data Index: 6398314 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.1303. Min Act: -0.1700
Data Index: 1971276 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.1303. Min Act: -0.1700
Data Index: 4195779 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.1303. Min Act: -0.1700
Data Index: 4763452 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.0678. Min Act: -0.1700
Data Index: 2521670 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.0678. Min Act: -0.1700
Data Index: 4404139 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.0365. Min Act: -0.1700
Data Index: 8136797 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.0365. Min Act: -0.1700
Data Index: 7084180 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5678. Min Range: -7.5678
Max Act: 7.0053. Min Act: -0.1700
Data Index: 2880099 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19