Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.1429. Min Act: -0.1700
Data Index: 2673561 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.0179. Min Act: -0.1700
Data Index: 2406539 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.0179. Min Act: -0.1700
Data Index: 5010805 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9866. Min Act: -0.1700
Data Index: 8090085 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9866. Min Act: -0.1700
Data Index: 2084808 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9866. Min Act: -0.1700
Data Index: 6650959 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9241. Min Act: -0.1700
Data Index: 1605969 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9553. Min Act: -0.1700
Data Index: 6763470 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9241. Min Act: -0.1700
Data Index: 7912149 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8928. Min Act: -0.1700
Data Index: 5199112 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 6634698 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8928. Min Act: -0.1700
Data Index: 2155433 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8928. Min Act: -0.1700
Data Index: 1748032 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8928. Min Act: -0.1700
Data Index: 2851346 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2092984 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 3811778 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 4222849 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 621605 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 700809 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 187106 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19