Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5661 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.9866. Min Act: -0.1700
Data Index: 7463455 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.7991. Min Act: -0.1700
Data Index: 3716224 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.7991. Min Act: -0.1700
Data Index: 4582944 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.7366. Min Act: -0.1700
Data Index: 5236991 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.7366. Min Act: -0.1700
Data Index: 3397403 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.6741. Min Act: -0.1700
Data Index: 8795377 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.6116. Min Act: -0.1700
Data Index: 4596743 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.6741. Min Act: -0.1700
Data Index: 4479627 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.5803. Min Act: -0.1700
Data Index: 421757 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.5803. Min Act: -0.1700
Data Index: 1531945 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.5178. Min Act: -0.1700
Data Index: 6530980 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.5178. Min Act: -0.1700
Data Index: 5276880 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.5178. Min Act: -0.1700
Data Index: 709564 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.4866. Min Act: -0.1700
Data Index: 3460118 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.4553. Min Act: -0.1700
Data Index: 151110 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.4553. Min Act: -0.1700
Data Index: 1776605 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.3928. Min Act: -0.1700
Data Index: 2223512 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.3616. Min Act: -0.1700
Data Index: 5426274 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.3928. Min Act: -0.1700
Data Index: 7503956 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9866. Min Range: -7.9866
Max Act: 7.3928. Min Act: -0.1700
Data Index: 2329422 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19