Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.8516. Min Act: -0.1700
Data Index: 8510610 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.7891. Min Act: -0.1700
Data Index: 8012910 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7432335 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.7266. Min Act: -0.1700
Data Index: 6218480 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.7266. Min Act: -0.1700
Data Index: 8727224 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6953. Min Act: -0.1700
Data Index: 3789160 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6328. Min Act: -0.1700
Data Index: 1163585 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6641. Min Act: -0.1700
Data Index: 3991802 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6641. Min Act: -0.1700
Data Index: 5058565 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6328. Min Act: -0.1700
Data Index: 8738687 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6328. Min Act: -0.1700
Data Index: 2937691 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.6016. Min Act: -0.1700
Data Index: 4351561 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5391. Min Act: -0.1700
Data Index: 2206273 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5703. Min Act: -0.1700
Data Index: 7005118 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5703. Min Act: -0.1700
Data Index: 304 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5703. Min Act: -0.1700
Data Index: 7618306 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5078. Min Act: -0.1700
Data Index: 1843947 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5078. Min Act: -0.1700
Data Index: 2957733 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.5078. Min Act: -0.1700
Data Index: 3616729 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8516. Min Range: -5.8516
Max Act: 5.4766. Min Act: -0.1700
Data Index: 6672613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19