Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1837. Min Range: -7.1837
Max Act: 7.1837. Min Act: -0.1700
Data Index: 6006147 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.5900. Min Act: -0.1700
Data Index: 1330954 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.5587. Min Act: -0.1700
Data Index: 7397851 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.5587. Min Act: -0.1700
Data Index: 6910277 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.5275. Min Act: -0.1700
Data Index: 6009017 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.4337. Min Act: -0.1700
Data Index: 1357205 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.4025. Min Act: -0.1700
Data Index: 7039790 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3712. Min Act: -0.1700
Data Index: 191857 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3507732 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3400. Min Act: -0.1700
Data Index: 8795519 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3087. Min Act: -0.1700
Data Index: 1715134 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3087. Min Act: -0.1700
Data Index: 962131 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.3087. Min Act: -0.1700
Data Index: 847242 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2775. Min Act: -0.1700
Data Index: 7814987 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2775. Min Act: -0.1700
Data Index: 3211627 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2775. Min Act: -0.1700
Data Index: 4790583 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2659227 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2420098 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2462. Min Act: -0.1700
Data Index: 4589398 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1837. Min Range: -7.1837
Max Act: 6.2462. Min Act: -0.1700
Data Index: 3081017 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19