Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.9959. Min Act: -0.1700
Data Index: 5120723 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5790833 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.6834. Min Act: -0.1700
Data Index: 860209 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.6209. Min Act: -0.1700
Data Index: 3268872 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.5897. Min Act: -0.1700
Data Index: 3780779 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.5584. Min Act: -0.1700
Data Index: 3912723 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.5272. Min Act: -0.1700
Data Index: 18275 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.5272. Min Act: -0.1700
Data Index: 1208867 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.5272. Min Act: -0.1700
Data Index: 7724273 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4334. Min Act: -0.1700
Data Index: 3097012 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4647. Min Act: -0.1700
Data Index: 7112650 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4334. Min Act: -0.1700
Data Index: 5177131 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4022. Min Act: -0.1700
Data Index: 8158327 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.3709. Min Act: -0.1700
Data Index: 8164478 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4334. Min Act: -0.1700
Data Index: 6569616 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4022. Min Act: -0.1700
Data Index: 2802719 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4334. Min Act: -0.1700
Data Index: 3672865 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4022. Min Act: -0.1700
Data Index: 4462531 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.4022. Min Act: -0.1700
Data Index: 6431656 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9959. Min Range: -5.9959
Max Act: 5.3709. Min Act: -0.1700
Data Index: 3750507 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19