Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.9182. Min Act: -0.1700
Data Index: 1151261 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.8499. Min Act: -0.1700
Data Index: 1814373 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.8499. Min Act: -0.1700
Data Index: 616420 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.8499. Min Act: -0.1700
Data Index: 6486633 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.8155. Min Act: -0.1700
Data Index: 558988 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7983. Min Act: -0.1700
Data Index: 5348121 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7811. Min Act: -0.1700
Data Index: 4779280 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7811. Min Act: -0.1700
Data Index: 4259725 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7811. Min Act: -0.1700
Data Index: 1652405 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 7410137 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 2073449 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 3104526 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1698
Data Index: 1331412 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7553. Min Act: -0.1700
Data Index: 1248500 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 7839192 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 5627656 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7553. Min Act: -0.1700
Data Index: 4413675 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7553. Min Act: -0.1700
Data Index: 3027467 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7553. Min Act: -0.1700
Data Index: 4629729 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9182. Min Range: -1.9182
Max Act: 1.7639. Min Act: -0.1700
Data Index: 62305 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19