Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4263 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8638. Min Act: -0.1700
Data Index: 4051138 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7388. Min Act: -0.1700
Data Index: 4565039 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7075. Min Act: -0.1700
Data Index: 735699 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5825. Min Act: -0.1700
Data Index: 929062 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 357094 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 5954987 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 2964477 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 6904321 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 3447377 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 3839167 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 4193546 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 7189746 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 8571834 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 3541720 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3638. Min Act: -0.1700
Data Index: 6680097 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3638. Min Act: -0.1700
Data Index: 1584168 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3638. Min Act: -0.1700
Data Index: 2242864 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3325. Min Act: -0.1700
Data Index: 2365320 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3638. Min Act: -0.1700
Data Index: 3782704 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3013. Min Act: -0.1700
Data Index: 511414 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19