Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.5990. Min Act: -0.1700
Data Index: 5812867 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.5365. Min Act: -0.1700
Data Index: 8470001 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.5365. Min Act: -0.1700
Data Index: 5323030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.5365. Min Act: -0.1700
Data Index: 6481670 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 6670064 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 6785536 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 3633275 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 7462699 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 3854001 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 7576975 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 4055829 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 278346 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 2389892 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 1005813 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1700
Data Index: 2072233 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 5348518 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4740. Min Act: -0.1699
Data Index: 4931619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 4348614 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 278345 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5990. Min Range: -6.5990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 4141155 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19