Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 3976022 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.3299. Min Act: -0.1700
Data Index: 6382660 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.2362. Min Act: -0.1700
Data Index: 5093012 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.1737. Min Act: -0.1700
Data Index: 1545960 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.1424. Min Act: -0.1700
Data Index: 6569495 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9862. Min Act: -0.1700
Data Index: 1559297 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5487. Min Range: -5.5487
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7710470 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 3569979 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 8808795 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9549. Min Act: -0.1700
Data Index: 4727529 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 5568451 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2797361 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2672009 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.9237. Min Act: -0.1700
Data Index: 6808973 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8612. Min Act: -0.1700
Data Index: 6156055 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8612. Min Act: -0.1700
Data Index: 1091680 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8299. Min Act: -0.1700
Data Index: 6967 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8299. Min Act: -0.1700
Data Index: 2337026 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8299. Min Act: -0.1700
Data Index: 5298291 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5487. Min Range: -5.5487
Max Act: 4.8924. Min Act: -0.1700
Data Index: 4329340 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19