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

Dataset: The Pile

Neuron 4942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1692804 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1768926 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1229145 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1232. Min Act: -0.0000

Data Index: 954409 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1158925 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1263866 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1154. Min Act: -0.0000

Data Index: 114475 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1151. Min Act: -0.0000

Data Index: 48032 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1179676 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1069251 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1847757 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1205. Min Act: -0.0000

Data Index: 436628 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1891829 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1509211 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1209458 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1147131 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1409456 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1046. Min Act: -0.0000

Data Index: 451389 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1147. Min Act: -0.0000

Data Index: 378986 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1002. Min Act: -0.0000

Data Index: 245681 (The Pile)

Max Activating Token Index: 948