Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.7731. Min Range: -11.7731
Max Act: 11.7731. Min Act: -0.1700
Data Index: 4740676 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.9606. Min Act: -0.1700
Data Index: 3484534 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.8981. Min Act: -0.1700
Data Index: 4462662 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.8981. Min Act: -0.1700
Data Index: 8719920 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.8981. Min Act: -0.1700
Data Index: 5875803 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.7731. Min Act: -0.1700
Data Index: 2913872 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.7731. Min Act: -0.1700
Data Index: 6143057 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.7106. Min Act: -0.1700
Data Index: 1023685 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.6481. Min Act: -0.1700
Data Index: 7316545 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.7106. Min Act: -0.1700
Data Index: 4852645 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5856. Min Act: -0.1700
Data Index: 7379454 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5856. Min Act: -0.1700
Data Index: 4507872 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5856. Min Act: -0.1700
Data Index: 6684490 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5231. Min Act: -0.1700
Data Index: 6143056 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5231. Min Act: -0.1700
Data Index: 5346400 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5231. Min Act: -0.1700
Data Index: 8032769 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5231. Min Act: -0.1700
Data Index: 2786176 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.5856. Min Act: -0.1700
Data Index: 528594 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.4606. Min Act: -0.1700
Data Index: 3484516 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7731. Min Range: -11.7731
Max Act: 10.4606. Min Act: -0.1700
Data Index: 6684486 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19