Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 7442054 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.8660. Min Act: -0.1700
Data Index: 5721010 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4483654 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4543701 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.8035. Min Act: -0.1700
Data Index: 2213072 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7723. Min Act: -0.1700
Data Index: 2651165 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7410. Min Act: -0.1700
Data Index: 4165681 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7410. Min Act: -0.1700
Data Index: 1832715 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7098. Min Act: -0.1700
Data Index: 4481667 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7334485 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7098. Min Act: -0.1700
Data Index: 1273319 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7337560 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.7098. Min Act: -0.1700
Data Index: 4165683 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4483652 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6785. Min Act: -0.1700
Data Index: 922628 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4896527 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4165685 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4165682 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6473. Min Act: -0.1700
Data Index: 2626467 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9910. Min Range: -5.9910
Max Act: 5.6473. Min Act: -0.1700
Data Index: 630092 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19