Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.9175. Min Act: -0.1700
Data Index: 8147280 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.6047. Min Act: -0.1700
Data Index: 2713327 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.5265. Min Act: -0.1700
Data Index: 7781956 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.5108. Min Act: -0.1700
Data Index: 6134490 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4638. Min Act: -0.1700
Data Index: 8768872 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4325. Min Act: -0.1700
Data Index: 57451 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4638. Min Act: -0.1700
Data Index: 6142368 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4638. Min Act: -0.1700
Data Index: 6787668 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4325. Min Act: -0.1700
Data Index: 8234335 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4325. Min Act: -0.1700
Data Index: 7679175 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4325. Min Act: -0.1700
Data Index: 1737806 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4325. Min Act: -0.1700
Data Index: 8830686 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4481. Min Act: -0.1700
Data Index: 3305836 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4168. Min Act: -0.1700
Data Index: 5661386 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.3854. Min Act: -0.1700
Data Index: 8752695 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.4011. Min Act: -0.1700
Data Index: 6787665 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.3854. Min Act: -0.1700
Data Index: 7544639 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.3698. Min Act: -0.1700
Data Index: 4272607 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.3698. Min Act: -0.1700
Data Index: 4773852 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9175. Min Range: -3.9175
Max Act: 3.3854. Min Act: -0.1700
Data Index: 5511603 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19