Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2323 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3541. Min Range: -9.3541
Max Act: 9.3541. Min Act: -0.1700
Data Index: 2884533 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.8541. Min Act: -0.1700
Data Index: 8043192 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.8541. Min Act: -0.1700
Data Index: 1730767 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.7916. Min Act: -0.1700
Data Index: 4616009 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.7916. Min Act: -0.1700
Data Index: 5979343 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 3179402 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.7291. Min Act: -0.1700
Data Index: 1446136 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.7291. Min Act: -0.1700
Data Index: 8025568 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 6397892 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 7104472 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 4509260 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 6120794 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 2426121 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6666. Min Act: -0.1700
Data Index: 4059124 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 4462568 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 548316 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 4813116 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 2684436 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.5416. Min Act: -0.1700
Data Index: 1604971 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3541. Min Range: -9.3541
Max Act: 8.6041. Min Act: -0.1700
Data Index: 3206814 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19