Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0045. Min Range: -9.0045
Max Act: 9.0045. Min Act: -0.1700
Data Index: 5873351 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.8170. Min Act: -0.1700
Data Index: 1109331 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.6920. Min Act: -0.1700
Data Index: 1537753 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5670. Min Act: -0.1700
Data Index: 4098677 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5670. Min Act: -0.1700
Data Index: 5666504 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5045. Min Act: -0.1700
Data Index: 1542043 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5045. Min Act: -0.1700
Data Index: 6867712 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5045. Min Act: -0.1700
Data Index: 5089263 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.4420. Min Act: -0.1700
Data Index: 6558540 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.4420. Min Act: -0.1700
Data Index: 6852504 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.5045. Min Act: -0.1700
Data Index: 351496 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 7499046 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 829931 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 82159 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 2581011 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 6277804 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1699
Data Index: 3066590 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3795. Min Act: -0.1700
Data Index: 6700986 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3170. Min Act: -0.1700
Data Index: 6255539 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0045. Min Range: -9.0045
Max Act: 8.3170. Min Act: -0.1700
Data Index: 3589410 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19