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

Dataset: The Pile

Neuron 517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3335. Min Act: -0.0000

Data Index: 277765 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2907. Min Act: -0.0000

Data Index: 614616 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1447968 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2242. Min Act: -0.0000

Data Index: 421833 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2312. Min Act: -0.0000

Data Index: 390965 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1583280 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2373. Min Act: -0.0000

Data Index: 584146 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2303. Min Act: -0.0000

Data Index: 753346 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2231. Min Act: -0.0000

Data Index: 785084 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1885569 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1310429 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1018977 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1265857 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1262249 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2584. Min Act: -0.0000

Data Index: 194782 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1868015 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1183201 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1533182 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1632288 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1741355 (The Pile)

Max Activating Token Index: 543