Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 779 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2563. Min Range: -7.2563
Max Act: 7.2563. Min Act: -0.1700
Data Index: 3024226 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2563. Min Range: -7.2563
Max Act: 7.1938. Min Act: -0.1700
Data Index: 774427 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2563. Min Range: -7.2563
Max Act: 7.0688. Min Act: -0.1700
Data Index: 8580702 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.7876. Min Act: -0.1700
Data Index: 4266569 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.7563. Min Act: -0.1700
Data Index: 106691 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.7251. Min Act: -0.1700
Data Index: 8361944 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.6626. Min Act: -0.1700
Data Index: 5390517 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.6001. Min Act: -0.1700
Data Index: 2368176 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.5688. Min Act: -0.1700
Data Index: 5981933 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.5688. Min Act: -0.1700
Data Index: 217807 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.5376. Min Act: -0.1700
Data Index: 1566809 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.5376. Min Act: -0.1700
Data Index: 8633123 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4751. Min Act: -0.1700
Data Index: 2926813 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4751. Min Act: -0.1700
Data Index: 3758851 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4438. Min Act: -0.1700
Data Index: 3929072 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4751. Min Act: -0.1700
Data Index: 2318108 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4126. Min Act: -0.1700
Data Index: 2497944 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.4126. Min Act: -0.1700
Data Index: 5564459 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.3813. Min Act: -0.1700
Data Index: 353666 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2563. Min Range: -7.2563
Max Act: 6.3501. Min Act: -0.1700
Data Index: 2026769 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19