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

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

Neuron 4519 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: 3.6126. Min Range: -3.6126

Max Act: 3.6126. Min Act: -0.0001

Data Index: 823183 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.2973. Min Act: -0.0001

Data Index: 1327400 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 3.6126. Min Range: -3.6126

Max Act: 3.0862. Min Act: -0.0001

Data Index: 1173033 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.9536. Min Act: -0.0001

Data Index: 744470 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.8434. Min Act: -0.0001

Data Index: 307667 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.5822. Min Act: -0.0001

Data Index: 804137 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.3558. Min Act: -0.0001

Data Index: 123495 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.3969. Min Act: -0.0001

Data Index: 366081 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.3959. Min Act: -0.0001

Data Index: 876258 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.2757. Min Act: -0.0001

Data Index: 932656 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.2224. Min Act: -0.0001

Data Index: 1086715 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.0918. Min Act: -0.0001

Data Index: 1251396 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.1666. Min Act: -0.0001

Data Index: 265483 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.1337. Min Act: -0.0001

Data Index: 1055487 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.1287. Min Act: -0.0001

Data Index: 112199 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.0312. Min Act: -0.0001

Data Index: 447526 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.0614. Min Act: -0.0001

Data Index: 358327 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.0407. Min Act: -0.0001

Data Index: 1267141 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.6126. Min Range: -3.6126

Max Act: 1.7561. Min Act: -0.0001

Data Index: 700776 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.6126. Min Range: -3.6126

Max Act: 2.0893. Min Act: -0.0001

Data Index: 645873 (C4 (Web Text))

Max Activating Token Index: 207