Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.6777. Min Act: -0.1700
Data Index: 2550480 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.6777. Min Act: -0.1700
Data Index: 3264004 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.5214. Min Act: -0.1700
Data Index: 5315327 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3964. Min Act: -0.1700
Data Index: 4095683 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7560803 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1964959 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3652. Min Act: -0.1700
Data Index: 5405209 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3652. Min Act: -0.1700
Data Index: 7211010 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3652. Min Act: -0.1700
Data Index: 5288116 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3027. Min Act: -0.1700
Data Index: 361310 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3652. Min Act: -0.1700
Data Index: 6378744 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3339. Min Act: -0.1700
Data Index: 3966233 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3339. Min Act: -0.1700
Data Index: 7560074 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.2714. Min Act: -0.1700
Data Index: 1370118 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3027. Min Act: -0.1700
Data Index: 430969 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.3027. Min Act: -0.1700
Data Index: 4988911 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.2714. Min Act: -0.1700
Data Index: 4087647 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.2714. Min Act: -0.1700
Data Index: 6310849 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.2714. Min Act: -0.1700
Data Index: 2186435 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6777. Min Range: -6.6777
Max Act: 6.2714. Min Act: -0.1700
Data Index: 2201017 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19