Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1299369 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1150411 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1344832 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.3893. Min Act: -0.0000

Data Index: 814914 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.3110. Min Act: -0.0000

Data Index: 194111 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2492. Min Act: -0.0000

Data Index: 595090 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2716. Min Act: -0.0000

Data Index: 184347 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2759. Min Act: -0.0000

Data Index: 110996 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2679. Min Act: -0.0000

Data Index: 496654 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2326. Min Act: -0.0000

Data Index: 95555 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1234445 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2672. Min Act: -0.0000

Data Index: 971017 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2289. Min Act: -0.0000

Data Index: 979255 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1770. Min Act: -0.0000

Data Index: 630836 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1524. Min Act: -0.0000

Data Index: 512191 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2062. Min Act: -0.0000

Data Index: 468188 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1951. Min Act: -0.0000

Data Index: 704177 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1621. Min Act: -0.0000

Data Index: 295792 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1516. Min Act: -0.0000

Data Index: 469018 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1874. Min Act: -0.0000

Data Index: 741716 (C4 (Web Text))

Max Activating Token Index: 88