Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2811 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2818. Min Act: -0.0000

Data Index: 914916 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1269868 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1784613 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2317. Min Act: -0.0001

Data Index: 683117 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1446929 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1961274 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2227. Min Act: -0.0000

Data Index: 572039 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1368985 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1316667 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1573270 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2104. Min Act: -0.0000

Data Index: 503286 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1219329 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1156040 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2023. Min Act: -0.0000

Data Index: 780875 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1854487 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1883. Min Act: -0.0000

Data Index: 938656 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1950. Min Act: -0.0000

Data Index: 391097 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1789342 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1527105 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1431731 (The Pile)

Max Activating Token Index: 508