Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.5152. Min Act: -0.1700
Data Index: 2465473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.3590. Min Act: -0.1699
Data Index: 8197537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.3277. Min Act: -0.1700
Data Index: 5589328 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2965. Min Act: -0.1700
Data Index: 1244345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2965. Min Act: -0.1700
Data Index: 3345691 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2340. Min Act: -0.1700
Data Index: 8263752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1699
Data Index: 8673440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1700
Data Index: 7441415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1700
Data Index: 7183886 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1698
Data Index: 1539433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2340. Min Act: -0.1700
Data Index: 211752 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 3800514 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2340. Min Act: -0.1699
Data Index: 3548078 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 6923949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 6009714 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 2085493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 4105023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 7010450 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 4200516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 8132147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19