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

Dataset: The Pile

Neuron 3129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4828. Min Act: -0.0000

Data Index: 642222 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1729339 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1156656 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.5213. Min Act: -0.0000

Data Index: 920471 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4553. Min Act: -0.0000

Data Index: 98924 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1628280 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4431. Min Act: -0.0000

Data Index: 827928 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4643. Min Act: -0.0000

Data Index: 975466 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4583. Min Act: -0.0000

Data Index: 211899 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1756855 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4303. Min Act: -0.0000

Data Index: 190269 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4297. Min Act: -0.0000

Data Index: 933876 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4408. Min Act: -0.0000

Data Index: 292620 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4166. Min Act: -0.0000

Data Index: 641251 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1477746 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4242. Min Act: -0.0000

Data Index: 958083 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4221. Min Act: -0.0000

Data Index: 368045 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1021050 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4186. Min Act: -0.0000

Data Index: 969910 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4159. Min Act: -0.0000

Data Index: 925304 (The Pile)

Max Activating Token Index: 821