Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.1198. Min Act: -0.1700
Data Index: 386517 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0886. Min Act: -0.1700
Data Index: 5326653 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0886. Min Act: -0.1700
Data Index: 3997049 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0573. Min Act: -0.1700
Data Index: 6674739 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0573. Min Act: -0.1700
Data Index: 431163 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0573. Min Act: -0.1700
Data Index: 2432219 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1198. Min Range: -6.1198
Max Act: 6.0261. Min Act: -0.1700
Data Index: 160343 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9948. Min Act: -0.1700
Data Index: 4481955 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9948. Min Act: -0.1700
Data Index: 2555359 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9948. Min Act: -0.1700
Data Index: 4550987 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 2591938 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9948. Min Act: -0.1700
Data Index: 3401994 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 188069 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 7391865 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 2013352 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 4859820 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9636. Min Act: -0.1700
Data Index: 4438091 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5814577 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9323. Min Act: -0.1700
Data Index: 5751010 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1198. Min Range: -6.1198
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5590002 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19