Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.8873. Min Act: -0.1700
Data Index: 3679003 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.6373. Min Act: -0.1700
Data Index: 2895402 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.5435. Min Act: -0.1700
Data Index: 5188065 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.5435. Min Act: -0.1700
Data Index: 660657 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.3873. Min Act: -0.1700
Data Index: 3916447 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1998. Min Act: -0.1700
Data Index: 7773855 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1998. Min Act: -0.1700
Data Index: 7144459 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1685. Min Act: -0.1700
Data Index: 3099972 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1685. Min Act: -0.1700
Data Index: 2486702 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1373. Min Act: -0.1700
Data Index: 2278827 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1060. Min Act: -0.1700
Data Index: 1917352 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.1373. Min Act: -0.1700
Data Index: 6106048 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.0435. Min Act: -0.1700
Data Index: 6228521 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.0123. Min Act: -0.1700
Data Index: 5451768 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.0123. Min Act: -0.1700
Data Index: 3405796 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8873. Min Range: -7.8873
Max Act: 7.0123. Min Act: -0.1700
Data Index: 7988658 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8873. Min Range: -7.8873
Max Act: 6.9810. Min Act: -0.1700
Data Index: 2143538 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8873. Min Range: -7.8873
Max Act: 6.9498. Min Act: -0.1700
Data Index: 4591418 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8873. Min Range: -7.8873
Max Act: 6.9810. Min Act: -0.1700
Data Index: 3508405 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8873. Min Range: -7.8873
Max Act: 6.9810. Min Act: -0.1700
Data Index: 1200565 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19