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

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

Neuron 3101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1148542 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1176495 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1322425 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2568. Min Act: -0.0000

Data Index: 16460 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2432. Min Act: -0.0000

Data Index: 47602 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2418. Min Act: -0.0000

Data Index: 377026 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2319. Min Act: -0.0000

Data Index: 974840 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2460. Min Act: -0.0000

Data Index: 454959 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1260001 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2243. Min Act: -0.0000

Data Index: 269298 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2034. Min Act: -0.0000

Data Index: 649289 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2140. Min Act: -0.0000

Data Index: 375351 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2155. Min Act: -0.0000

Data Index: 676140 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2181. Min Act: -0.0000

Data Index: 188260 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2213. Min Act: -0.0000

Data Index: 968996 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1127235 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1242088 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1216240 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2007. Min Act: -0.0000

Data Index: 419482 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1991. Min Act: -0.0000

Data Index: 868192 (C4 (Web Text))

Max Activating Token Index: 798