Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.8479. Min Act: -0.1700
Data Index: 8167652 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6916. Min Act: -0.1700
Data Index: 7202124 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6916. Min Act: -0.1700
Data Index: 2919419 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6916. Min Act: -0.1700
Data Index: 483622 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6916. Min Act: -0.1700
Data Index: 449307 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6291. Min Act: -0.1700
Data Index: 7648133 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5979. Min Act: -0.1700
Data Index: 2989653 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 4579653 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 8820404 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 7490840 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 192980 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5041. Min Act: -0.1700
Data Index: 4698521 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4729. Min Act: -0.1700
Data Index: 566250 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4729. Min Act: -0.1700
Data Index: 1261645 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4416. Min Act: -0.1700
Data Index: 2032696 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5041. Min Act: -0.1700
Data Index: 1004059 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4729. Min Act: -0.1700
Data Index: 3482433 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4104. Min Act: -0.1700
Data Index: 4491767 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4416. Min Act: -0.1700
Data Index: 5537664 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.4729. Min Act: -0.1700
Data Index: 7811917 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19