Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1068710 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1347401 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1326942 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1513778 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2360. Min Act: -0.0001

Data Index: 317859 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2269. Min Act: -0.0000

Data Index: 662841 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2090. Min Act: -0.0000

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2119. Min Act: -0.0000

Data Index: 867499 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1990. Min Act: -0.0000

Data Index: 570810 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1967. Min Act: -0.0000

Data Index: 935370 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1262389 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2097. Min Act: -0.0000

Data Index: 876256 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2208. Min Act: -0.0000

Data Index: 776872 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1628399 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1266041 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1999. Min Act: -0.0000

Data Index: 121344 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2086. Min Act: -0.0000

Data Index: 376173 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1382694 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1638221 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1622753 (Python Code)

Max Activating Token Index: 384