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

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

Neuron 1598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0002

Data Index: 693420 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2353. Min Act: -0.0002

Data Index: 800944 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2277. Min Act: -0.0002

Data Index: 1202617 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2237. Min Act: -0.0002

Data Index: 418024 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2384. Min Act: -0.0002

Data Index: 1264422 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2277. Min Act: -0.0002

Data Index: 875092 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2425. Min Act: -0.0002

Data Index: 473625 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2125. Min Act: -0.0002

Data Index: 212619 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2154. Min Act: -0.0002

Data Index: 390737 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2145. Min Act: -0.0002

Data Index: 1026229 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1998. Min Act: -0.0002

Data Index: 594824 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2118. Min Act: -0.0002

Data Index: 666674 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1995. Min Act: -0.0002

Data Index: 1241993 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2034. Min Act: -0.0002

Data Index: 1042416 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2203. Min Act: -0.0002

Data Index: 60442 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2251. Min Act: -0.0002

Data Index: 906419 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2112. Min Act: -0.0002

Data Index: 528086 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2081. Min Act: -0.0002

Data Index: 755791 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1200913 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2222. Min Act: -0.0002

Data Index: 494969 (C4 (Web Text))

Max Activating Token Index: 796