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

Dataset: The Pile

Neuron 3035 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2228. Min Act: -0.0000

Data Index: 779790 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1716. Min Act: -0.0000

Data Index: 510957 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1336076 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1517. Min Act: -0.0000

Data Index: 26123 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1645. Min Act: -0.0000

Data Index: 28258 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1030369 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1648304 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1726895 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1737207 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1850344 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1479584 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1206333 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1310. Min Act: -0.0000

Data Index: 623981 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1262. Min Act: -0.0000

Data Index: 976524 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1388. Min Act: -0.0000

Data Index: 801427 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1161140 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1233. Min Act: -0.0000

Data Index: 425917 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1759624 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1700698 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1191. Min Act: -0.0000

Data Index: 830118 (The Pile)

Max Activating Token Index: 827