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

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

Neuron 2365 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0515. Min Act: -0.0003

Data Index: 175243 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0405. Min Act: -0.0002

Data Index: 531713 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0358. Min Act: -0.0003

Data Index: 417479 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0310. Min Act: -0.0002

Data Index: 823181 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1125760 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0314. Min Act: -0.0003

Data Index: 369406 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0308. Min Act: -0.0003

Data Index: 638080 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1134586 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1202275 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0304. Min Act: -0.0003

Data Index: 318644 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0288. Min Act: -0.0002

Data Index: 828240 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0288. Min Act: -0.0002

Data Index: 708318 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1541124 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1376579 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0275. Min Act: -0.0003

Data Index: 403204 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0280. Min Act: -0.0003

Data Index: 41977 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0270. Min Act: -0.0003

Data Index: 853819 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1327683 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1229303 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0269. Min Act: -0.0003

Data Index: 96169 (C4 (Web Text))

Max Activating Token Index: 900