Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0394. Min Range: -4.0394
Max Act: 4.0394. Min Act: -0.1700
Data Index: 2971296 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.9613. Min Act: -0.1700
Data Index: 6291336 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.9300. Min Act: -0.1700
Data Index: 7197038 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.9300. Min Act: -0.1700
Data Index: 1069533 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.9300. Min Act: -0.1700
Data Index: 3254466 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.9144. Min Act: -0.1700
Data Index: 7345645 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.8206. Min Act: -0.1700
Data Index: 2317876 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.8049. Min Act: -0.1700
Data Index: 1712821 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7737. Min Act: -0.1700
Data Index: 2633901 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7737. Min Act: -0.1700
Data Index: 5669328 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7893. Min Act: -0.1700
Data Index: 904362 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7737. Min Act: -0.1700
Data Index: 5687700 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7580. Min Act: -0.1700
Data Index: 2317875 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7580. Min Act: -0.1700
Data Index: 6312104 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7580. Min Act: -0.1700
Data Index: 721018 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7268. Min Act: -0.1700
Data Index: 200393 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7111. Min Act: -0.1700
Data Index: 2603136 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.7268. Min Act: -0.1700
Data Index: 145173 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.6955. Min Act: -0.1700
Data Index: 662092 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0394. Min Range: -4.0394
Max Act: 3.6642. Min Act: -0.1700
Data Index: 1979510 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19