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

Dataset: The Pile

Neuron 2166 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0644. Min Act: -0.0000

Data Index: 665463 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1676320 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1893720 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9943. Min Act: -0.0000

Data Index: 190873 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1665797 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1844278 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1869101 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1213454 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1122004 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1479221 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1523490 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0075. Min Act: -0.0000

Data Index: 316101 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8710. Min Act: -0.0000

Data Index: 382770 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1170334 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1440042 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1786099 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1581158 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8490. Min Act: -0.0000

Data Index: 217329 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8386. Min Act: -0.0000

Data Index: 900965 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1188327 (The Pile)

Max Activating Token Index: 304