Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4302. Min Range: -8.4302
Max Act: 8.4302. Min Act: -0.1700
Data Index: 1649162 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.8052. Min Act: -0.1700
Data Index: 1172914 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.9302. Min Act: -0.1700
Data Index: 745004 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.8052. Min Act: -0.1700
Data Index: 8470221 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.8052. Min Act: -0.1700
Data Index: 3195765 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.7427. Min Act: -0.1700
Data Index: 8640044 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.7427. Min Act: -0.1700
Data Index: 4840432 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.6177. Min Act: -0.1700
Data Index: 5112916 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.5552. Min Act: -0.1700
Data Index: 3160527 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 7402775 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 639626 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 2521334 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4302. Min Act: -0.1700
Data Index: 6215757 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 381223 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 7667895 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4927. Min Act: -0.1700
Data Index: 7163897 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4302. Min Act: -0.1700
Data Index: 3288708 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4302. Min Act: -0.1700
Data Index: 339313 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4302. Min Act: -0.1700
Data Index: 6300904 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4302. Min Range: -8.4302
Max Act: 7.4302. Min Act: -0.1700
Data Index: 8290424 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19