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

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

Neuron 2138 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: 0.1560. Min Range: -0.1560

Max Act: 0.1472. Min Act: -0.0001

Data Index: 924920 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1152211 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0001

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1458. Min Act: -0.0001

Data Index: 348558 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1428. Min Act: -0.0001

Data Index: 977126 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1213392 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1407. Min Act: -0.0001

Data Index: 415425 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1329. Min Act: -0.0001

Data Index: 820433 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1275. Min Act: -0.0001

Data Index: 575123 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1345784 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1244. Min Act: -0.0001

Data Index: 538131 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1319. Min Act: -0.0001

Data Index: 33237 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1334. Min Act: -0.0001

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1228. Min Act: -0.0001

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1073007 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1193. Min Act: -0.0001

Data Index: 599780 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1019310 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1071513 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1154. Min Act: -0.0001

Data Index: 148910 (C4 (Web Text))

Max Activating Token Index: 661