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

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

Neuron 3453 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.4350. Min Act: -0.0000

Data Index: 583076 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1332933 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1445948 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.3339. Min Act: -0.0000

Data Index: 400662 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1348554 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2115. Min Act: -0.0000

Data Index: 535208 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1284388 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1310318 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2211. Min Act: -0.0000

Data Index: 228028 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2254. Min Act: -0.0000

Data Index: 479651 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1690. Min Act: -0.0000

Data Index: 90762 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1625734 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1720. Min Act: -0.0000

Data Index: 648037 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1658. Min Act: -0.0000

Data Index: 870421 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1279698 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0298. Min Act: 0.0000

Data Index: 662274 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1024. Min Act: -0.0000

Data Index: 475383 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1178233 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1240684 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0655. Min Act: -0.0000

Data Index: 537269 (C4 (Web Text))

Max Activating Token Index: 571