Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.4029. Min Act: -0.1700
Data Index: 7866004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3852. Min Act: -0.1700
Data Index: 5962902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3676. Min Act: -0.1700
Data Index: 3853990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3764. Min Act: -0.1700
Data Index: 4595418 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3588. Min Act: -0.1700
Data Index: 6762696 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3588. Min Act: -0.1700
Data Index: 3965649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3588. Min Act: -0.1700
Data Index: 4610876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3588. Min Act: -0.1700
Data Index: 2242228 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3588. Min Act: -0.1700
Data Index: 5481402 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3500. Min Act: -0.1700
Data Index: 6018264 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 2913263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 1296483 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 6622290 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 8717992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 5364532 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 6708743 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 5794435 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3323. Min Act: -0.1700
Data Index: 6282828 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3412. Min Act: -0.1700
Data Index: 7597752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4029. Min Range: -1.4029
Max Act: 1.3323. Min Act: -0.1700
Data Index: 4429613 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19