Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.1353. Min Act: -0.1700
Data Index: 2827732 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.1019. Min Act: -0.1700
Data Index: 7565555 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.1019. Min Act: -0.1700
Data Index: 6984550 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0851. Min Act: -0.1700
Data Index: 3957415 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0347. Min Act: -0.1700
Data Index: 5019399 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 5216368 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0347. Min Act: -0.1700
Data Index: 5153801 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0347. Min Act: -0.1700
Data Index: 3303413 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 7226947 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 2689061 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 1147699 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 5451374 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 1083566 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 4786459 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 1519153 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0347. Min Act: -0.1700
Data Index: 4245783 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 916824 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1699
Data Index: 7944188 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0178. Min Act: -0.1700
Data Index: 1536518 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1353. Min Range: -2.1353
Max Act: 2.0009. Min Act: -0.1700
Data Index: 6431639 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19