Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1633 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.5320. Min Act: -0.1700
Data Index: 3892875 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.4695. Min Act: -0.1700
Data Index: 5887326 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.4383. Min Act: -0.1700
Data Index: 4180229 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.4070. Min Act: -0.1700
Data Index: 5146178 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8546448 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.3758. Min Act: -0.1700
Data Index: 5544812 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.3445. Min Act: -0.1700
Data Index: 792681 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.3445. Min Act: -0.1700
Data Index: 2085256 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.3133. Min Act: -0.1700
Data Index: 388440 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.3133. Min Act: -0.1700
Data Index: 2449868 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2820. Min Act: -0.1700
Data Index: 7710460 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2820. Min Act: -0.1700
Data Index: 6813625 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2508. Min Act: -0.1700
Data Index: 8300305 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2508. Min Act: -0.1700
Data Index: 6014846 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2508. Min Act: -0.1700
Data Index: 611741 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2508. Min Act: -0.1700
Data Index: 8428861 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.2195. Min Act: -0.1700
Data Index: 4934508 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.1883. Min Act: -0.1700
Data Index: 4820146 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.1883. Min Act: -0.1700
Data Index: 1505828 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5320. Min Range: -5.5320
Max Act: 5.1883. Min Act: -0.1700
Data Index: 1642938 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19