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

Dataset: The Pile

Neuron 4035 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: 0.2211. Min Range: -0.2211

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1494308 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2037. Min Act: -0.0000

Data Index: 66452 (The Pile)

Max Activating Token Index: 319

Text #2

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1371914 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1898888 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1474. Min Act: -0.0000

Data Index: 118299 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1817070 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1111470 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1380754 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1344772 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1237. Min Act: -0.0000

Data Index: 172918 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1163. Min Act: -0.0000

Data Index: 881979 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1280. Min Act: -0.0000

Data Index: 688210 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1207. Min Act: -0.0000

Data Index: 706661 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1686384 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1830297 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1553139 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1744390 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1072. Min Act: -0.0000

Data Index: 662792 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1107. Min Act: -0.0000

Data Index: 878758 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1123. Min Act: -0.0000

Data Index: 588733 (The Pile)

Max Activating Token Index: 631