Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.3343. Min Act: -0.0001

Data Index: 675764 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2946. Min Act: -0.0001

Data Index: 75221 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2739. Min Act: -0.0000

Data Index: 414570 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2546. Min Act: -0.0001

Data Index: 819170 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2527. Min Act: -0.0001

Data Index: 348917 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2654. Min Act: -0.0000

Data Index: 727972 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1189288 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2376. Min Act: -0.0001

Data Index: 711694 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2292. Min Act: -0.0000

Data Index: 229058 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1014109 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1228288 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2168. Min Act: -0.0001

Data Index: 226931 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1023598 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2203. Min Act: -0.0000

Data Index: 579475 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1143613 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2058. Min Act: -0.0000

Data Index: 227062 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1262644 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2265. Min Act: -0.0001

Data Index: 606908 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2037. Min Act: -0.0001

Data Index: 309443 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2108. Min Act: -0.0001

Data Index: 715377 (C4 (Web Text))

Max Activating Token Index: 631