Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.7346. Min Act: -0.1700
Data Index: 45664 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.6721. Min Act: -0.1700
Data Index: 17803 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.6408. Min Act: -0.1700
Data Index: 2310821 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.6408. Min Act: -0.1700
Data Index: 8489190 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.6408. Min Act: -0.1700
Data Index: 1225698 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.6096. Min Act: -0.1700
Data Index: 7471105 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5471. Min Act: -0.1700
Data Index: 6056966 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5471. Min Act: -0.1700
Data Index: 45665 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5471. Min Act: -0.1700
Data Index: 3535075 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5471. Min Act: -0.1700
Data Index: 7327030 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5158. Min Act: -0.1700
Data Index: 4989665 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5158. Min Act: -0.1700
Data Index: 1050985 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5158. Min Act: -0.1700
Data Index: 5500912 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5158. Min Act: -0.1700
Data Index: 1050984 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.5158. Min Act: -0.1700
Data Index: 6702750 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.4533. Min Act: -0.1700
Data Index: 1890808 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.4533. Min Act: -0.1700
Data Index: 828950 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.3908. Min Act: -0.1700
Data Index: 3200085 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.4221. Min Act: -0.1700
Data Index: 970749 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7346. Min Range: -5.7346
Max Act: 5.4533. Min Act: -0.1700
Data Index: 1119405 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19