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

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

Neuron 3687 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0000

Data Index: 674428 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1211922 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0316. Min Act: -0.0000

Data Index: 84770 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0000

Data Index: 1609307 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0307. Min Act: -0.0000

Data Index: 1655929 (Python Code)

Max Activating Token Index: 592

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0312. Min Act: -0.0000

Data Index: 322074 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0304. Min Act: -0.0000

Data Index: 70709 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1065745 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0276. Min Act: -0.0000

Data Index: 21858 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0278. Min Act: -0.0000

Data Index: 865300 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0261. Min Act: -0.0000

Data Index: 884045 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0262. Min Act: -0.0000

Data Index: 226734 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0256. Min Act: -0.0000

Data Index: 341566 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0257. Min Act: -0.0000

Data Index: 9166 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0251. Min Act: -0.0000

Data Index: 513923 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1547442 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1545903 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0267. Min Act: -0.0000

Data Index: 893293 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0246. Min Act: -0.0000

Data Index: 926790 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0253. Min Act: -0.0000

Data Index: 458213 (C4 (Web Text))

Max Activating Token Index: 45