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

Dataset: The Pile

Neuron 1869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.7222. Min Act: -0.0000

Data Index: 53530 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6440. Min Act: -0.0000

Data Index: 180219 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1494999 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1235540 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5651. Min Act: -0.0000

Data Index: 945695 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1101547 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1880882 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1818441 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5609. Min Act: -0.0000

Data Index: 538833 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5551. Min Act: -0.0000

Data Index: 720849 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1544932 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1820667 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5165. Min Act: -0.0000

Data Index: 904521 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5155. Min Act: -0.0000

Data Index: 414659 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1887549 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1339339 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1072777 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1401443 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1399122 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5004. Min Act: -0.0000

Data Index: 46671 (The Pile)

Max Activating Token Index: 368