Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6826. Min Range: -7.6826
Max Act: 7.6826. Min Act: -0.1700
Data Index: 1997978 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6826. Min Range: -7.6826
Max Act: 7.5888. Min Act: -0.1700
Data Index: 6384415 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6826. Min Range: -7.6826
Max Act: 7.1201. Min Act: -0.1700
Data Index: 8615645 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6826. Min Range: -7.6826
Max Act: 7.0888. Min Act: -0.1700
Data Index: 1447098 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6826. Min Range: -7.6826
Max Act: 7.0576. Min Act: -0.1700
Data Index: 4533595 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.9951. Min Act: -0.1700
Data Index: 5025553 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.9951. Min Act: -0.1700
Data Index: 1803626 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.9951. Min Act: -0.1700
Data Index: 7799986 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.9638. Min Act: -0.1700
Data Index: 7714997 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.8701. Min Act: -0.1700
Data Index: 89310 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.8701. Min Act: -0.1700
Data Index: 1677246 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.8076. Min Act: -0.1700
Data Index: 2922243 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.8076. Min Act: -0.1700
Data Index: 2160189 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7763. Min Act: -0.1700
Data Index: 4205245 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5819916 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.8076. Min Act: -0.1700
Data Index: 2398829 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7451. Min Act: -0.1700
Data Index: 8066747 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7138. Min Act: -0.1700
Data Index: 1030803 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7138. Min Act: -0.1700
Data Index: 5263098 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6826. Min Range: -7.6826
Max Act: 6.7138. Min Act: -0.1700
Data Index: 1634371 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19