Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.6595. Min Act: -0.1700
Data Index: 8363289 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.6595. Min Act: -0.1700
Data Index: 5194627 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.4720. Min Act: -0.1700
Data Index: 5876910 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.3470. Min Act: -0.1700
Data Index: 5960564 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.2845. Min Act: -0.1700
Data Index: 3648726 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.2845. Min Act: -0.1700
Data Index: 6719124 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.2220. Min Act: -0.1700
Data Index: 4267521 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.2220. Min Act: -0.1700
Data Index: 1337347 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.2220. Min Act: -0.1700
Data Index: 513140 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.1595. Min Act: -0.1700
Data Index: 863949 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0970. Min Act: -0.1700
Data Index: 2028353 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0970. Min Act: -0.1700
Data Index: 4565152 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 8116742 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 6435502 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 4430179 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6595. Min Range: -8.6595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 658109 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6595. Min Range: -8.6595
Max Act: 7.9720. Min Act: -0.1700
Data Index: 5999556 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6595. Min Range: -8.6595
Max Act: 7.9720. Min Act: -0.1700
Data Index: 4521124 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6595. Min Range: -8.6595
Max Act: 7.9095. Min Act: -0.1700
Data Index: 7294038 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6595. Min Range: -8.6595
Max Act: 7.9720. Min Act: -0.1700
Data Index: 5663402 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19