Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2458. Min Act: -0.0000

Data Index: 43135 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1729. Min Act: -0.0000

Data Index: 611725 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1472. Min Act: -0.0000

Data Index: 238947 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1662. Min Act: -0.0000

Data Index: 186243 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1258408 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1458. Min Act: -0.0000

Data Index: 349123 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1553966 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1272. Min Act: -0.0000

Data Index: 496768 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1975074 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1260466 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1848452 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1250. Min Act: -0.0000

Data Index: 333961 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1489279 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1297. Min Act: -0.0000

Data Index: 711204 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1198. Min Act: -0.0000

Data Index: 881848 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1692849 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1976988 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1997568 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1631045 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1264. Min Act: -0.0000

Data Index: 393204 (The Pile)

Max Activating Token Index: 878