Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3329. Min Range: -6.3329
Max Act: 6.3329. Min Act: -0.1700
Data Index: 1949266 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3329. Min Range: -6.3329
Max Act: 6.1454. Min Act: -0.1700
Data Index: 6269147 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3329. Min Range: -6.3329
Max Act: 6.0517. Min Act: -0.1700
Data Index: 4316759 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3329. Min Range: -6.3329
Max Act: 6.0517. Min Act: -0.1700
Data Index: 4124828 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3329. Min Range: -6.3329
Max Act: 6.0204. Min Act: -0.1700
Data Index: 2166564 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.9892. Min Act: -0.1700
Data Index: 7283388 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.8954. Min Act: -0.1700
Data Index: 4267259 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.9267. Min Act: -0.1700
Data Index: 486387 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.9267. Min Act: -0.1700
Data Index: 7419420 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4316765 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.8329. Min Act: -0.1700
Data Index: 1525879 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7704. Min Act: -0.1700
Data Index: 2318978 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7392. Min Act: -0.1700
Data Index: 3648633 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7704. Min Act: -0.1700
Data Index: 6716736 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7392. Min Act: -0.1700
Data Index: 2993987 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7079. Min Act: -0.1700
Data Index: 8805687 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3628349 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.6454. Min Act: -0.1700
Data Index: 6054109 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.6767. Min Act: -0.1700
Data Index: 1786375 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3329. Min Range: -6.3329
Max Act: 5.6767. Min Act: -0.1700
Data Index: 964583 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19