Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3292. Min Act: -0.0000

Data Index: 468222 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3145. Min Act: -0.0000

Data Index: 256040 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2981. Min Act: -0.0000

Data Index: 515012 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1505158 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2563. Min Act: -0.0000

Data Index: 47943 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2550. Min Act: -0.0000

Data Index: 632496 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2594. Min Act: -0.0000

Data Index: 251020 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1067533 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1577932 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2252. Min Act: -0.0000

Data Index: 419112 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1561395 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2356. Min Act: -0.0001

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1419938 (Python Code)

Max Activating Token Index: 604

Text #13

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2189. Min Act: -0.0000

Data Index: 635873 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1595282 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1614245 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1391613 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2264. Min Act: -0.0000

Data Index: 174704 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1375083 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1400725 (Python Code)

Max Activating Token Index: 863