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

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

Neuron 1567 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.2575. Min Act: -0.0000

Data Index: 138198 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1565. Min Act: -0.0000

Data Index: 852140 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1577. Min Act: -0.0000

Data Index: 909495 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1119636 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1463. Min Act: -0.0000

Data Index: 34507 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1112141 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1062091 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1335. Min Act: -0.0000

Data Index: 305443 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1353. Min Act: -0.0000

Data Index: 336903 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1336. Min Act: -0.0000

Data Index: 719462 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1332. Min Act: -0.0000

Data Index: 752025 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1239. Min Act: -0.0000

Data Index: 666840 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1326. Min Act: -0.0000

Data Index: 13110 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1211493 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1040293 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1348. Min Act: -0.0000

Data Index: 63018 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1163. Min Act: -0.0000

Data Index: 264715 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1290. Min Act: -0.0000

Data Index: 557675 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1248. Min Act: -0.0000

Data Index: 738356 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1200501 (C4 (Web Text))

Max Activating Token Index: 438