Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3391357 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.6108. Min Act: -0.1700
Data Index: 4815570 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5795. Min Act: -0.1700
Data Index: 3397789 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5638. Min Act: -0.1700
Data Index: 167329 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5482. Min Act: -0.1700
Data Index: 8775018 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5482. Min Act: -0.1700
Data Index: 4627152 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5482. Min Act: -0.1700
Data Index: 3188666 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 6861760 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5169. Min Act: -0.1700
Data Index: 3696231 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 7042636 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5169. Min Act: -0.1700
Data Index: 3188629 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5325. Min Act: -0.1700
Data Index: 4042741 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.4855. Min Act: -0.1700
Data Index: 6916574 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 7153651 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 825178 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5169. Min Act: -0.1700
Data Index: 4103678 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 2875972 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 1848646 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.4855. Min Act: -0.1700
Data Index: 6140730 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6421. Min Range: -3.6421
Max Act: 3.5012. Min Act: -0.1700
Data Index: 5705916 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19