Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.7884. Min Act: -0.1700
Data Index: 8567563 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.6634. Min Act: -0.1700
Data Index: 1589476 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.6322. Min Act: -0.1700
Data Index: 1589493 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.5384. Min Act: -0.1700
Data Index: 2538187 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.4447. Min Act: -0.1700
Data Index: 8567570 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.4447. Min Act: -0.1700
Data Index: 8504035 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.4447. Min Act: -0.1700
Data Index: 3794318 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.4447. Min Act: -0.1700
Data Index: 4415501 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.3822. Min Act: -0.1700
Data Index: 8567564 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.3197. Min Act: -0.1700
Data Index: 8504040 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 3794334 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 8504039 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4415488 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4742645 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2884. Min Act: -0.1700
Data Index: 3378126 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 5657918 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 5056231 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 3378123 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 8128941 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7884. Min Range: -7.7884
Max Act: 7.2572. Min Act: -0.1700
Data Index: 4742666 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19