Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5363. Min Range: -8.5363
Max Act: 8.5363. Min Act: -0.1700
Data Index: 1963747 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5363. Min Range: -8.5363
Max Act: 8.0363. Min Act: -0.1700
Data Index: 4187083 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5363. Min Range: -8.5363
Max Act: 8.0676. Min Act: -0.1700
Data Index: 2654627 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.7863. Min Act: -0.1700
Data Index: 7394918 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.7551. Min Act: -0.1700
Data Index: 7009203 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.7238. Min Act: -0.1700
Data Index: 3407136 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.6301. Min Act: -0.1700
Data Index: 3270452 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.4738. Min Act: -0.1700
Data Index: 6501809 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3801. Min Act: -0.1700
Data Index: 5004548 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3488. Min Act: -0.1700
Data Index: 3270457 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3488. Min Act: -0.1700
Data Index: 6368923 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3488. Min Act: -0.1700
Data Index: 7638997 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3176. Min Act: -0.1700
Data Index: 3327730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.3488. Min Act: -0.1700
Data Index: 3748161 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2551. Min Act: -0.1700
Data Index: 3174192 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2551. Min Act: -0.1700
Data Index: 1201971 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2551. Min Act: -0.1700
Data Index: 6689927 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2863. Min Act: -0.1700
Data Index: 4531572 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2551. Min Act: -0.1700
Data Index: 4823074 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5363. Min Range: -8.5363
Max Act: 7.2238. Min Act: -0.1700
Data Index: 4460900 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19