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

Dataset: The Pile

Neuron 698 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: 1.3251. Min Range: -1.3251

Max Act: 1.3251. Min Act: -0.0000

Data Index: 421444 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1767227 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1627102 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2878. Min Act: -0.0000

Data Index: 12097 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3227. Min Act: -0.0000

Data Index: 960430 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0887. Min Act: -0.0000

Data Index: 15984 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1031. Min Act: -0.0000

Data Index: 596558 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1638514 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1214. Min Act: -0.0000

Data Index: 728572 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1609326 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0824. Min Act: -0.0000

Data Index: 732033 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1107. Min Act: -0.0000

Data Index: 60027 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1723. Min Act: -0.0000

Data Index: 546161 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1244996 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1458941 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0739. Min Act: -0.0000

Data Index: 962435 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2054. Min Act: -0.0000

Data Index: 237030 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1573. Min Act: -0.0000

Data Index: 303145 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1247. Min Act: -0.0000

Data Index: 1696171 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.2071. Min Act: -0.0000

Data Index: 647814 (The Pile)

Max Activating Token Index: 761