Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1239 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0326. Min Range: -10.0326
Max Act: 10.0326. Min Act: -0.1700
Data Index: 583711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.7826. Min Act: -0.1700
Data Index: 583698 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.6576. Min Act: -0.1700
Data Index: 6161543 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.6576. Min Act: -0.1700
Data Index: 553445 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.4701. Min Act: -0.1700
Data Index: 4613464 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.4076. Min Act: -0.1700
Data Index: 5517813 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.4076. Min Act: -0.1700
Data Index: 8021986 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.4076. Min Act: -0.1700
Data Index: 873205 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.3451. Min Act: -0.1700
Data Index: 1762730 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.3451. Min Act: -0.1700
Data Index: 1259064 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2826. Min Act: -0.1700
Data Index: 6040711 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2826. Min Act: -0.1700
Data Index: 727551 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2201. Min Act: -0.1700
Data Index: 5671378 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2826. Min Act: -0.1700
Data Index: 7603647 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2201. Min Act: -0.1700
Data Index: 1186055 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2201. Min Act: -0.1700
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.2826. Min Act: -0.1700
Data Index: 6074710 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.0951. Min Act: -0.1700
Data Index: 2889033 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.0951. Min Act: -0.1700
Data Index: 6939228 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0326. Min Range: -10.0326
Max Act: 9.0951. Min Act: -0.1700
Data Index: 5482582 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19