Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1365 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.8967. Min Act: -0.1700
Data Index: 1273919 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.8029. Min Act: -0.1700
Data Index: 1674420 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.7404. Min Act: -0.1700
Data Index: 6847657 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.7092. Min Act: -0.1700
Data Index: 6315254 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.7092. Min Act: -0.1700
Data Index: 87594 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.6779. Min Act: -0.1700
Data Index: 1967699 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5529. Min Act: -0.1700
Data Index: 72194 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5782165 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5217. Min Act: -0.1700
Data Index: 3040182 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5217. Min Act: -0.1700
Data Index: 2793740 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 7031515 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5217. Min Act: -0.1700
Data Index: 68664 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 6491580 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 4926779 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 3111948 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 265602 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.5217. Min Act: -0.1700
Data Index: 690384 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4904. Min Act: -0.1700
Data Index: 5242862 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4592. Min Act: -0.1700
Data Index: 1758968 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8967. Min Range: -4.8967
Max Act: 4.4592. Min Act: -0.1700
Data Index: 6460561 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19