Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.5291. Min Act: -0.1700
Data Index: 6753672 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.4041. Min Act: -0.1700
Data Index: 1820431 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.2478. Min Act: -0.1700
Data Index: 3686872 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1853. Min Act: -0.1700
Data Index: 4458458 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1541. Min Act: -0.1700
Data Index: 7712215 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1541. Min Act: -0.1700
Data Index: 2422507 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1228. Min Act: -0.1700
Data Index: 986928 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1228. Min Act: -0.1700
Data Index: 700473 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0916. Min Act: -0.1700
Data Index: 4565360 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.1228. Min Act: -0.1700
Data Index: 2237226 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0916. Min Act: -0.1700
Data Index: 4332997 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2267925 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2760012 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2618977 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0291. Min Act: -0.1700
Data Index: 6987378 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5291. Min Range: -6.5291
Max Act: 6.0291. Min Act: -0.1700
Data Index: 4810380 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5291. Min Range: -6.5291
Max Act: 5.9978. Min Act: -0.1700
Data Index: 6318233 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5291. Min Range: -6.5291
Max Act: 5.9978. Min Act: -0.1700
Data Index: 5384559 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5291. Min Range: -6.5291
Max Act: 5.9978. Min Act: -0.1700
Data Index: 4541871 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5291. Min Range: -6.5291
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4360568 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19