Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5794 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.9560. Min Act: -0.1700
Data Index: 780197 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.8310. Min Act: -0.1700
Data Index: 6287763 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.7685. Min Act: -0.1700
Data Index: 117396 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.7060. Min Act: -0.1700
Data Index: 3927889 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6748. Min Act: -0.1700
Data Index: 4638609 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6748. Min Act: -0.1700
Data Index: 3595177 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6748. Min Act: -0.1700
Data Index: 2591423 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6748. Min Act: -0.1700
Data Index: 3432492 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6123. Min Act: -0.1700
Data Index: 1163005 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6748. Min Act: -0.1700
Data Index: 458809 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2568239 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.6435. Min Act: -0.1700
Data Index: 283559 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.5498. Min Act: -0.1700
Data Index: 2678859 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.5498. Min Act: -0.1700
Data Index: 476120 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.5185. Min Act: -0.1700
Data Index: 4135687 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.5185. Min Act: -0.1700
Data Index: 4712451 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.4873. Min Act: -0.1700
Data Index: 8671990 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.4873. Min Act: -0.1700
Data Index: 4209041 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.4873. Min Act: -0.1700
Data Index: 3064864 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9560. Min Range: -5.9560
Max Act: 5.4560. Min Act: -0.1700
Data Index: 3995579 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19