Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.5691. Min Act: -0.1700
Data Index: 8366539 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.5378. Min Act: -0.1700
Data Index: 1978605 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.5066. Min Act: -0.1700
Data Index: 5789491 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.4128. Min Act: -0.1700
Data Index: 5628497 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.4441. Min Act: -0.1700
Data Index: 552769 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.4441. Min Act: -0.1700
Data Index: 856402 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3816. Min Act: -0.1700
Data Index: 3655298 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3816. Min Act: -0.1700
Data Index: 2420246 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3503. Min Act: -0.1700
Data Index: 1934084 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3503. Min Act: -0.1700
Data Index: 4246922 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 5273504 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 5262046 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 2168911 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 2030034 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 180056 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.3191. Min Act: -0.1700
Data Index: 8104770 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.2878. Min Act: -0.1700
Data Index: 36986 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.2878. Min Act: -0.1700
Data Index: 3229140 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.2878. Min Act: -0.1700
Data Index: 756492 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5691. Min Range: -4.5691
Max Act: 4.2566. Min Act: -0.1700
Data Index: 1823 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19