Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.4618. Min Act: -0.1700
Data Index: 5330421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.4305. Min Act: -0.1700
Data Index: 8391417 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3680. Min Act: -0.1700
Data Index: 1577114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7110606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3368. Min Act: -0.1700
Data Index: 2817520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3368. Min Act: -0.1700
Data Index: 804493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 7360354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 1380649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 2944792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 5993693 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 2216036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.3055. Min Act: -0.1700
Data Index: 7971310 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2743. Min Act: -0.1700
Data Index: 7685695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2430. Min Act: -0.1700
Data Index: 8762566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2430. Min Act: -0.1700
Data Index: 1073550 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2743. Min Act: -0.1700
Data Index: 1210766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2743. Min Act: -0.1700
Data Index: 1033832 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2743. Min Act: -0.1700
Data Index: 6670976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2430. Min Act: -0.1700
Data Index: 7966795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4618. Min Range: -4.4618
Max Act: 4.2743. Min Act: -0.1700
Data Index: 3149910 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19