Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.8479. Min Act: -0.1700
Data Index: 745283 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4624854 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.7854. Min Act: -0.1700
Data Index: 1472959 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.7229. Min Act: -0.1700
Data Index: 6696564 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.7229. Min Act: -0.1700
Data Index: 2245981 (Open Web Text)
Max Activating Token Index: 520
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: 7273154 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6291. Min Act: -0.1700
Data Index: 8502798 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.6291. Min Act: -0.1700
Data Index: 5863449 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5979. Min Act: -0.1700
Data Index: 3806959 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5979. Min Act: -0.1700
Data Index: 8585782 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5354. Min Act: -0.1700
Data Index: 2611029 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 3665460 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 3665596 (Open Web Text)
Max Activating Token Index: 131
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: 91287 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5666. Min Act: -0.1700
Data Index: 4853423 (Open Web Text)
Max Activating Token Index: 562
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: 1966056 (Open Web Text)
Max Activating Token Index: 583
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: 7340757 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5041. Min Act: -0.1700
Data Index: 2115048 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5041. Min Act: -0.1700
Data Index: 6331818 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8479. Min Range: -6.8479
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5375466 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19