Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 416 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.6015. Min Act: -0.1700
Data Index: 8664751 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 8293136 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 5027778 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4140. Min Act: -0.1700
Data Index: 7241747 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2890. Min Act: -0.1700
Data Index: 8092257 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3203. Min Act: -0.1700
Data Index: 5608063 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2578. Min Act: -0.1700
Data Index: 5591786 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1953. Min Act: -0.1700
Data Index: 818866 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1953. Min Act: -0.1700
Data Index: 601352 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 8106632 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0703. Min Act: -0.1700
Data Index: 4037136 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7702800 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0390. Min Act: -0.1700
Data Index: 6863169 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 6135557 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0078. Min Act: -0.1700
Data Index: 6838154 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.0078. Min Act: -0.1700
Data Index: 448318 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3986964 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 4704085 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 4587476 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6015. Min Range: -6.6015
Max Act: 5.9765. Min Act: -0.1700
Data Index: 7063698 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19