Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4991 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0978. Min Range: -7.0978
Max Act: 7.0978. Min Act: -0.1700
Data Index: 7361437 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0978. Min Range: -7.0978
Max Act: 7.0353. Min Act: -0.1700
Data Index: 4338725 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0978. Min Range: -7.0978
Max Act: 7.0040. Min Act: -0.1700
Data Index: 3755635 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.9415. Min Act: -0.1700
Data Index: 8655613 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.9728. Min Act: -0.1700
Data Index: 4668386 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.9415. Min Act: -0.1700
Data Index: 4800271 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.9415. Min Act: -0.1700
Data Index: 2741335 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.8790. Min Act: -0.1700
Data Index: 2931942 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 5340402 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.8165. Min Act: -0.1700
Data Index: 3398657 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1584620 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 326638 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7540. Min Act: -0.1700
Data Index: 1808349 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 8635631 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7540. Min Act: -0.1700
Data Index: 4735455 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7540. Min Act: -0.1700
Data Index: 8653964 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 147267 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7540. Min Act: -0.1700
Data Index: 6823438 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7853. Min Act: -0.1700
Data Index: 4335611 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0978. Min Range: -7.0978
Max Act: 6.7228. Min Act: -0.1700
Data Index: 5748249 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19