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

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

Neuron 1843 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1057434 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2873. Min Act: -0.0000

Data Index: 298413 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2667. Min Act: -0.0000

Data Index: 85834 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2491. Min Act: -0.0000

Data Index: 891434 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1348058 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2317. Min Act: -0.0000

Data Index: 309889 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2119. Min Act: -0.0000

Data Index: 392686 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2321. Min Act: -0.0000

Data Index: 552492 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2165. Min Act: -0.0000

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1047423 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2145. Min Act: -0.0000

Data Index: 779800 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2417. Min Act: -0.0000

Data Index: 674585 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1214900 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2161. Min Act: -0.0000

Data Index: 293250 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2020. Min Act: -0.0000

Data Index: 376215 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.1997. Min Act: -0.0000

Data Index: 748838 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1304763 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1533486 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 0.3280. Min Range: -0.3280

Max Act: 0.2037. Min Act: -0.0000

Data Index: 703498 (C4 (Web Text))

Max Activating Token Index: 171