Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.8381. Min Act: -0.1700
Data Index: 3717857 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.8063. Min Act: -0.1700
Data Index: 1942240 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.7904. Min Act: -0.1700
Data Index: 3600488 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.7744. Min Act: -0.1700
Data Index: 600675 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.7585. Min Act: -0.1700
Data Index: 1905260 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.7265. Min Act: -0.1700
Data Index: 7068987 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.6625. Min Act: -0.1700
Data Index: 7037559 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.6304. Min Act: -0.1700
Data Index: 5435081 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.6304. Min Act: -0.1700
Data Index: 1339979 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.6143. Min Act: -0.1700
Data Index: 5536318 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5983. Min Act: -0.1700
Data Index: 2513976 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.6143. Min Act: -0.1700
Data Index: 1715712 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5821. Min Act: -0.1700
Data Index: 8825568 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5983. Min Act: -0.1700
Data Index: 6612375 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5821. Min Act: -0.1700
Data Index: 8214214 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5821. Min Act: -0.1700
Data Index: 7778530 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5660. Min Act: -0.1700
Data Index: 7871915 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5821. Min Act: -0.1700
Data Index: 7622885 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5660. Min Act: -0.1700
Data Index: 878601 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8381. Min Range: -2.8381
Max Act: 2.5821. Min Act: -0.1700
Data Index: 3286715 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19