Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1142. Min Range: -7.1142
Max Act: 7.1142. Min Act: -0.1700
Data Index: 4493525 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.9579. Min Act: -0.1700
Data Index: 2712523 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.9267. Min Act: -0.1700
Data Index: 4392156 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.8329. Min Act: -0.1700
Data Index: 2657887 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.8954. Min Act: -0.1700
Data Index: 2030182 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.8329. Min Act: -0.1700
Data Index: 994272 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.8017. Min Act: -0.1700
Data Index: 6441471 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.7392. Min Act: -0.1700
Data Index: 3647672 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.7704. Min Act: -0.1700
Data Index: 3708807 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.7392. Min Act: -0.1700
Data Index: 5993415 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.7079. Min Act: -0.1700
Data Index: 452182 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6454. Min Act: -0.1700
Data Index: 5592755 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.7079. Min Act: -0.1700
Data Index: 1106889 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6767. Min Act: -0.1700
Data Index: 2034886 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6767. Min Act: -0.1700
Data Index: 5469606 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6454. Min Act: -0.1700
Data Index: 6119117 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6454. Min Act: -0.1700
Data Index: 8643003 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.6767. Min Act: -0.1700
Data Index: 3407294 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.5829. Min Act: -0.1700
Data Index: 4308645 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1142. Min Range: -7.1142
Max Act: 6.5829. Min Act: -0.1700
Data Index: 7128080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19