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

Dataset: The Pile

Neuron 3212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1787755 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3332. Min Act: -0.0000

Data Index: 541837 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1723215 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1717738 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2656. Min Act: -0.0000

Data Index: 575459 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2575. Min Act: -0.0000

Data Index: 139316 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2498. Min Act: -0.0000

Data Index: 149746 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2350. Min Act: -0.0000

Data Index: 677277 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2481. Min Act: -0.0000

Data Index: 681061 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1299072 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2510. Min Act: -0.0000

Data Index: 724079 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1557640 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2311. Min Act: -0.0000

Data Index: 196173 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2275. Min Act: -0.0000

Data Index: 833766 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1297900 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1478217 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2312. Min Act: -0.0000

Data Index: 336595 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1406044 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1319045 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1743468 (The Pile)

Max Activating Token Index: 703