Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2765. Min Range: -12.2765
Max Act: 12.2765. Min Act: -0.1700
Data Index: 975859 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2765. Min Range: -12.2765
Max Act: 12.2140. Min Act: -0.1700
Data Index: 6820185 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2765. Min Range: -12.2765
Max Act: 12.1515. Min Act: -0.1700
Data Index: 698382 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2765. Min Range: -12.2765
Max Act: 12.0890. Min Act: -0.1700
Data Index: 7264494 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.8390. Min Act: -0.1700
Data Index: 1782049 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.6515. Min Act: -0.1700
Data Index: 1962872 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.5890. Min Act: -0.1700
Data Index: 4645781 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.5265. Min Act: -0.1700
Data Index: 3312172 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.4640. Min Act: -0.1700
Data Index: 6520499 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.4640. Min Act: -0.1700
Data Index: 2307687 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.4015. Min Act: -0.1700
Data Index: 273287 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.4015. Min Act: -0.1700
Data Index: 7969619 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.4015. Min Act: -0.1700
Data Index: 2684239 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.3390. Min Act: -0.1700
Data Index: 8831177 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.3390. Min Act: -0.1700
Data Index: 7680341 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.3390. Min Act: -0.1700
Data Index: 7426232 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.3390. Min Act: -0.1700
Data Index: 4603915 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.3390. Min Act: -0.1700
Data Index: 1682379 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.2765. Min Act: -0.1700
Data Index: 2052168 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2765. Min Range: -12.2765
Max Act: 11.2765. Min Act: -0.1700
Data Index: 1396518 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19