Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9992. Min Act: -0.1700
Data Index: 7189763 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9679. Min Act: -0.1700
Data Index: 1261393 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9679. Min Act: -0.1700
Data Index: 8367013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 2723567 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 8130656 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9367. Min Act: -0.1700
Data Index: 8650004 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9367. Min Act: -0.1700
Data Index: 937372 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 1785929 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9367. Min Act: -0.1700
Data Index: 6212274 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 2987989 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9367. Min Act: -0.1700
Data Index: 6271156 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 2011606 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 3074097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 8077178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 1585102 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8429. Min Act: -0.1700
Data Index: 5542210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8429. Min Act: -0.1700
Data Index: 2247968 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 707167 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 4062465 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8429. Min Act: -0.1700
Data Index: 7084809 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19