Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6003 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.7681. Min Act: -0.1700
Data Index: 7579060 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.5181. Min Act: -0.1700
Data Index: 5572820 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.4868. Min Act: -0.1700
Data Index: 2588995 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.4556. Min Act: -0.1700
Data Index: 7342072 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.4243. Min Act: -0.1700
Data Index: 456252 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.4556. Min Act: -0.1700
Data Index: 5376068 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.3618. Min Act: -0.1700
Data Index: 1171364 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.3306. Min Act: -0.1700
Data Index: 4783953 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 63073 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2681. Min Act: -0.1700
Data Index: 169165 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 7178906 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 5517359 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2056. Min Act: -0.1700
Data Index: 8002889 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2056. Min Act: -0.1700
Data Index: 6910897 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2056. Min Act: -0.1700
Data Index: 8589224 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 6600768 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.2056. Min Act: -0.1700
Data Index: 3529621 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.1743. Min Act: -0.1700
Data Index: 180076 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.1743. Min Act: -0.1700
Data Index: 8134837 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7681. Min Range: -5.7681
Max Act: 5.1431. Min Act: -0.1700
Data Index: 6691129 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19