Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6627. Min Range: -8.6627
Max Act: 8.6627. Min Act: -0.1700
Data Index: 4758140 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6627. Min Range: -8.6627
Max Act: 8.1002. Min Act: -0.1700
Data Index: 6843291 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.9440. Min Act: -0.1700
Data Index: 8662201 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.8190. Min Act: -0.1700
Data Index: 2697552 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.6627. Min Act: -0.1700
Data Index: 4314989 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.6627. Min Act: -0.1700
Data Index: 367826 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.5690. Min Act: -0.1700
Data Index: 6292201 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.5377. Min Act: -0.1700
Data Index: 5399298 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.5377. Min Act: -0.1700
Data Index: 3902257 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.4440. Min Act: -0.1700
Data Index: 7239987 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.4440. Min Act: -0.1700
Data Index: 5610011 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.4440. Min Act: -0.1700
Data Index: 2732741 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.3815. Min Act: -0.1700
Data Index: 446510 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.3815. Min Act: -0.1700
Data Index: 760145 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.3190. Min Act: -0.1700
Data Index: 4735628 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.2877. Min Act: -0.1700
Data Index: 1515850 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.2877. Min Act: -0.1700
Data Index: 2912878 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.2877. Min Act: -0.1700
Data Index: 7340551 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.2252. Min Act: -0.1700
Data Index: 5283384 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6627. Min Range: -8.6627
Max Act: 7.1940. Min Act: -0.1700
Data Index: 7239982 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19