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

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

Neuron 2899 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1386770 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1479546 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.2515. Min Act: -0.0001

Data Index: 173664 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1357781 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1327. Min Act: -0.0001

Data Index: 771239 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1316. Min Act: -0.0001

Data Index: 547355 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1408124 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1415473 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1154. Min Act: -0.0001

Data Index: 383987 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1395917 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1587625 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1213368 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1011. Min Act: -0.0001

Data Index: 677721 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1136. Min Act: -0.0001

Data Index: 334629 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1401231 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1073. Min Act: -0.0001

Data Index: 437284 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.1037. Min Act: -0.0001

Data Index: 364969 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.0922. Min Act: -0.0001

Data Index: 506381 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1378615 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.2515. Min Range: -0.2515

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1260463 (C4 (Web Text))

Max Activating Token Index: 52