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

Dataset: The Pile

Neuron 3769 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: 0.8316. Min Range: -0.8316

Max Act: 0.8316. Min Act: -0.0000

Data Index: 218156 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1461371 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1713512 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1946981 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7193. Min Act: -0.0000

Data Index: 257202 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6613. Min Act: -0.0000

Data Index: 554294 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7171. Min Act: -0.0000

Data Index: 969381 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1517974 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1347681 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1244362 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6239. Min Act: -0.0000

Data Index: 137072 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6373. Min Act: -0.0000

Data Index: 55579 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5750. Min Act: -0.0000

Data Index: 887078 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1267148 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6183. Min Act: -0.0000

Data Index: 840088 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1177664 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1806601 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5388. Min Act: 0.0000

Data Index: 1221104 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1399075 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1416370 (The Pile)

Max Activating Token Index: 951