Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7976676 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6208. Min Act: -0.1700
Data Index: 7530486 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5895. Min Act: -0.1700
Data Index: 3872942 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5895. Min Act: -0.1700
Data Index: 1213271 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5583. Min Act: -0.1700
Data Index: 5854274 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5270. Min Act: -0.1700
Data Index: 3872941 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5270. Min Act: -0.1700
Data Index: 7976675 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 6888631 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 3724164 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 6667328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 6368214 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 3457123 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 6321532 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 1972372 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 5166769 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6015246 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6307372 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 4705201 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 2138955 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 1023598 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19