Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2305 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.7169. Min Act: -0.1700
Data Index: 1723384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.7087. Min Act: -0.1700
Data Index: 2343036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.7005. Min Act: -0.1700
Data Index: 7893565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6843. Min Act: -0.1700
Data Index: 8602674 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6762. Min Act: -0.1700
Data Index: 6425683 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6762. Min Act: -0.1699
Data Index: 3104804 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6600. Min Act: -0.1700
Data Index: 8065362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6843. Min Act: -0.1700
Data Index: 3970997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6681. Min Act: -0.1700
Data Index: 7051930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 5926767 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 13519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 2533181 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 3560587 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 6385598 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 7936692 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6439. Min Act: -0.1700
Data Index: 6657774 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6439. Min Act: -0.1700
Data Index: 7253638 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6520. Min Act: -0.1700
Data Index: 918693 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6360. Min Act: -0.1700
Data Index: 3644107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7169. Min Range: -0.7169
Max Act: 0.6280. Min Act: -0.1700
Data Index: 7880658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19