Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0211. Min Range: -5.0211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 407561 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9274. Min Act: -0.1700
Data Index: 547701 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.9274. Min Act: -0.1700
Data Index: 6168442 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 7084531 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 6890428 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 7297663 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 3119747 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 1784519 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 2209482 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 4665952 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1614126 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 1566484 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8336. Min Act: -0.1700
Data Index: 3470823 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 5394983 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1050010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 7924013 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 4996970 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8336. Min Act: -0.1700
Data Index: 2480588 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8336. Min Act: -0.1700
Data Index: 6647866 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0211. Min Range: -5.0211
Max Act: 4.8649. Min Act: -0.1700
Data Index: 7010569 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19