Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.7191. Min Act: -0.1694
Data Index: 4066671 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6702. Min Act: -0.1697
Data Index: 2418546 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6702. Min Act: -0.1700
Data Index: 3195621 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6541. Min Act: -0.1700
Data Index: 2297322 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6541. Min Act: -0.1660
Data Index: 2418563 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6222. Min Act: -0.1700
Data Index: 8306841 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6222. Min Act: -0.1700
Data Index: 1250546 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6222. Min Act: -0.1700
Data Index: 2948061 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6063. Min Act: -0.1660
Data Index: 2418566 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6063. Min Act: -0.1700
Data Index: 2152628 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.6063. Min Act: -0.1700
Data Index: 6158190 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5906. Min Act: -0.1700
Data Index: 6829726 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5906. Min Act: -0.1700
Data Index: 3174580 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5906. Min Act: -0.1700
Data Index: 4041636 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5750. Min Act: -0.1700
Data Index: 1974225 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5906. Min Act: -0.1699
Data Index: 5119999 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5906. Min Act: -0.1700
Data Index: 432531 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5750. Min Act: -0.1700
Data Index: 1055935 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5750. Min Act: -0.1699
Data Index: 2516732 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7191. Min Range: -0.7191
Max Act: 0.5595. Min Act: -0.1700
Data Index: 4740602 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19