Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.2266. Min Act: -0.1700
Data Index: 571680 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 8240230 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 314817 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 122816 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0079. Min Act: -0.1700
Data Index: 3039782 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0079. Min Act: -0.1700
Data Index: 6839933 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9766. Min Act: -0.1700
Data Index: 922267 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9454. Min Act: -0.1700
Data Index: 1872517 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.8829. Min Act: -0.1700
Data Index: 968264 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.8516. Min Act: -0.1700
Data Index: 6910549 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.8204. Min Act: -0.1700
Data Index: 7462691 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7891. Min Act: -0.1700
Data Index: 7072174 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7891. Min Act: -0.1700
Data Index: 4342343 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7891. Min Act: -0.1700
Data Index: 2940624 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7891. Min Act: -0.1700
Data Index: 4041057 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7579. Min Act: -0.1700
Data Index: 3911101 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7891. Min Act: -0.1700
Data Index: 5885817 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7579. Min Act: -0.1700
Data Index: 7198412 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7579. Min Act: -0.1700
Data Index: 5642163 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.7579. Min Act: -0.1700
Data Index: 3476532 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19