Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1151 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.9507. Min Act: -0.1700
Data Index: 5643595 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.9195. Min Act: -0.1700
Data Index: 8164335 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.7632. Min Act: -0.1700
Data Index: 1177829 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.7007. Min Act: -0.1700
Data Index: 4796728 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.7007. Min Act: -0.1700
Data Index: 5340141 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.7007. Min Act: -0.1700
Data Index: 1511904 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.6070. Min Act: -0.1700
Data Index: 7040902 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.5757. Min Act: -0.1700
Data Index: 2487855 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.5445. Min Act: -0.1700
Data Index: 6108508 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.5132. Min Act: -0.1700
Data Index: 839059 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.5132. Min Act: -0.1700
Data Index: 3004236 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4820. Min Act: -0.1700
Data Index: 5686714 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.5132. Min Act: -0.1700
Data Index: 8663515 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4195. Min Act: -0.1700
Data Index: 2648508 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4507. Min Act: -0.1700
Data Index: 4302144 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4820. Min Act: -0.1700
Data Index: 1755567 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4195. Min Act: -0.1700
Data Index: 7314998 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4195. Min Act: -0.1700
Data Index: 168864 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4195. Min Act: -0.1700
Data Index: 405394 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9507. Min Range: -7.9507
Max Act: 7.4195. Min Act: -0.1700
Data Index: 2730624 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19