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

Dataset: The Pile

Neuron 874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1132381 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1675627 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0850. Min Act: -0.0000

Data Index: 153969 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1154010 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9197. Min Act: -0.0000

Data Index: 822523 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1291042 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1629501 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9487. Min Act: -0.0000

Data Index: 13191 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1035071 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9564. Min Act: -0.0000

Data Index: 769441 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1735311 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8833. Min Act: -0.0000

Data Index: 83464 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8817. Min Act: -0.0000

Data Index: 207641 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9446. Min Act: -0.0000

Data Index: 185233 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9701. Min Act: -0.0000

Data Index: 360737 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9380. Min Act: -0.0000

Data Index: 696992 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8854. Min Act: -0.0000

Data Index: 809896 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1358002 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9079. Min Act: -0.0000

Data Index: 246202 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1943732 (The Pile)

Max Activating Token Index: 735