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

Dataset: The Pile

Neuron 656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1299. Min Act: -0.0000

Data Index: 178767 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1309054 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1110. Min Act: -0.0000

Data Index: 603075 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1449749 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1273672 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1119. Min Act: -0.0000

Data Index: 840740 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1246. Min Act: -0.0000

Data Index: 703914 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1023. Min Act: -0.0000

Data Index: 501519 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1109. Min Act: -0.0000

Data Index: 579241 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1728706 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1023. Min Act: -0.0000

Data Index: 330842 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1872653 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1080536 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0927. Min Act: -0.0000

Data Index: 64349 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0959. Min Act: -0.0000

Data Index: 969271 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0934. Min Act: -0.0000

Data Index: 153802 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1864327 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1419845 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0935. Min Act: -0.0000

Data Index: 274305 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1111882 (The Pile)

Max Activating Token Index: 701