Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.9303. Min Act: -0.1700
Data Index: 2467200 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.7116. Min Act: -0.1700
Data Index: 3640316 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.7116. Min Act: -0.1700
Data Index: 2662752 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.6803. Min Act: -0.1700
Data Index: 4808014 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.6491. Min Act: -0.1700
Data Index: 1823840 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.6178. Min Act: -0.1700
Data Index: 8415886 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.6178. Min Act: -0.1700
Data Index: 95508 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.5553. Min Act: -0.1700
Data Index: 6360543 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.5553. Min Act: -0.1700
Data Index: 8693204 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.5241. Min Act: -0.1700
Data Index: 7798311 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.4928. Min Act: -0.1700
Data Index: 3813547 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.4928. Min Act: -0.1700
Data Index: 6948940 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.4303. Min Act: -0.1700
Data Index: 4694774 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3991. Min Act: -0.1700
Data Index: 6024123 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3991. Min Act: -0.1700
Data Index: 3005766 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3678. Min Act: -0.1700
Data Index: 4583568 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3678. Min Act: -0.1700
Data Index: 1078462 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3678. Min Act: -0.1700
Data Index: 3074864 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3678. Min Act: -0.1700
Data Index: 4995197 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9303. Min Range: -5.9303
Max Act: 5.3678. Min Act: -0.1700
Data Index: 6383990 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19