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

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

Neuron 2878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0001

Data Index: 917762 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2604. Min Act: -0.0001

Data Index: 450961 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2608. Min Act: -0.0001

Data Index: 593270 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1335880 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1019468 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1140792 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2384. Min Act: -0.0001

Data Index: 527219 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2430. Min Act: -0.0001

Data Index: 508614 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2202. Min Act: -0.0001

Data Index: 678308 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2164. Min Act: -0.0001

Data Index: 304667 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2207. Min Act: -0.0001

Data Index: 465958 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2108. Min Act: -0.0001

Data Index: 511544 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2168. Min Act: -0.0001

Data Index: 62325 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1110699 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2225. Min Act: -0.0001

Data Index: 717493 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2023. Min Act: -0.0001

Data Index: 644449 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1140876 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2119. Min Act: -0.0001

Data Index: 978756 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2001. Min Act: -0.0001

Data Index: 366947 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1065351 (C4 (Web Text))

Max Activating Token Index: 739