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

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

Neuron 4488 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.4369. Min Act: -0.0000

Data Index: 693141 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.2308. Min Act: -0.0000

Data Index: 489839 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.1416. Min Act: -0.0000

Data Index: 771577 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.1262. Min Act: -0.0000

Data Index: 828244 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.1287. Min Act: -0.0000

Data Index: 612665 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1330616 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9672. Min Act: -0.0000

Data Index: 385028 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1288223 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0225. Min Act: -0.0000

Data Index: 476893 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.2372. Min Act: -0.0000

Data Index: 995901 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1113093 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0137. Min Act: -0.0000

Data Index: 86683 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1109128 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0965. Min Act: -0.0000

Data Index: 1111353 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.0141. Min Act: -0.0000

Data Index: 352986 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 1.4369. Min Range: -1.4369

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1180445 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9572. Min Act: -0.0001

Data Index: 1296624 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9888. Min Act: -0.0000

Data Index: 288413 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1055113 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.4369. Min Range: -1.4369

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1008396 (C4 (Web Text))

Max Activating Token Index: 694