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

Dataset: The Pile

Neuron 2931 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: 1.2059. Min Range: -1.2059

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1272845 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1684153 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7075. Min Act: -0.0000

Data Index: 936106 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1726286 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1969722 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7302. Min Act: -0.0000

Data Index: 303337 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8178. Min Act: -0.0000

Data Index: 94410 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1663789 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1637811 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8196. Min Act: -0.0000

Data Index: 732193 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1225856 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1804469 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1394417 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7203. Min Act: -0.0000

Data Index: 808466 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7367. Min Act: -0.0000

Data Index: 541984 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1684038 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7585. Min Act: -0.0000

Data Index: 55348 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1457420 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1035816 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7014. Min Act: -0.0000

Data Index: 7091 (The Pile)

Max Activating Token Index: 384