Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6803761 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.9352. Min Act: -0.1700
Data Index: 5818419 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.7789. Min Act: -0.1700
Data Index: 4871676 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.6852. Min Act: -0.1700
Data Index: 8437927 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.6539. Min Act: -0.1700
Data Index: 6566409 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.6227. Min Act: -0.1700
Data Index: 3033699 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5914. Min Act: -0.1700
Data Index: 2602333 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5602. Min Act: -0.1700
Data Index: 8642463 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5602. Min Act: -0.1700
Data Index: 5725142 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5289. Min Act: -0.1700
Data Index: 4890245 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5602. Min Act: -0.1700
Data Index: 5280283 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.5289. Min Act: -0.1700
Data Index: 5050843 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6710924 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2139810 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 1184985 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 5243120 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 3177413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 2622687 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 1335528 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9977. Min Range: -4.9977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 2454912 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19