Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 856 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.4698. Min Act: -0.1700
Data Index: 8081949 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.4072. Min Act: -0.1700
Data Index: 7259486 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.4072. Min Act: -0.1700
Data Index: 7441532 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.4072. Min Act: -0.1700
Data Index: 4035667 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3447. Min Act: -0.1700
Data Index: 834708 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3447. Min Act: -0.1700
Data Index: 4197684 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3447. Min Act: -0.1700
Data Index: 6542933 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3447. Min Act: -0.1700
Data Index: 8312674 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3447. Min Act: -0.1700
Data Index: 6283800 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3135. Min Act: -0.1700
Data Index: 6728377 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2822. Min Act: -0.1700
Data Index: 4990397 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2822. Min Act: -0.1700
Data Index: 5389496 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.3135. Min Act: -0.1700
Data Index: 1721317 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2197. Min Act: -0.1700
Data Index: 3134242 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2822. Min Act: -0.1700
Data Index: 2705756 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2822. Min Act: -0.1700
Data Index: 7566425 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2822. Min Act: -0.1700
Data Index: 8341036 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2510. Min Act: -0.1700
Data Index: 5877591 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2510. Min Act: -0.1700
Data Index: 8020054 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4698. Min Range: -4.4698
Max Act: 4.2197. Min Act: -0.1700
Data Index: 6259511 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19