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

Dataset: The Pile

Neuron 2797 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: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1951879 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0381. Min Act: -0.0000

Data Index: 743246 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0311. Min Act: -0.0000

Data Index: 268859 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0302. Min Act: -0.0000

Data Index: 880647 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1159059 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1271219 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0206. Min Act: -0.0000

Data Index: 848124 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1578860 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0220. Min Act: -0.0000

Data Index: 1848572 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0225. Min Act: -0.0000

Data Index: 420560 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0212. Min Act: -0.0000

Data Index: 179634 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0158. Min Act: -0.0000

Data Index: 225934 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0170. Min Act: -0.0000

Data Index: 1363429 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0191. Min Act: -0.0000

Data Index: 3983 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0196. Min Act: -0.0000

Data Index: 123686 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0204. Min Act: -0.0000

Data Index: 1627828 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1846114 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0146. Min Act: -0.0000

Data Index: 1877872 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0175. Min Act: -0.0000

Data Index: 1085201 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0162. Min Act: -0.0000

Data Index: 1217857 (The Pile)

Max Activating Token Index: 333