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

Dataset: The Pile

Neuron 3691 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: 1.1173. Min Range: -1.1173

Max Act: 1.1173. Min Act: -0.0000

Data Index: 283913 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 1.1173. Min Range: -1.1173

Max Act: 1.1141. Min Act: -0.0000

Data Index: 839717 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 1.1173. Min Range: -1.1173

Max Act: 1.0353. Min Act: -0.0000

Data Index: 921695 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 1.1173. Min Range: -1.1173

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1317312 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1850131 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.9625. Min Act: -0.0000

Data Index: 284502 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.9204. Min Act: -0.0000

Data Index: 652940 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8507. Min Act: -0.0000

Data Index: 117677 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8589. Min Act: -0.0000

Data Index: 848726 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8227. Min Act: -0.0000

Data Index: 491992 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1795070 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1314182 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1151414 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1648480 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7620. Min Act: -0.0000

Data Index: 601231 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1011042 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7993. Min Act: 0.0000

Data Index: 214015 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1381899 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1165224 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 1.1173. Min Range: -1.1173

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1578688 (The Pile)

Max Activating Token Index: 975