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

Dataset: The Pile

Neuron 2209 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1515619 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9047. Min Act: -0.0000

Data Index: 849469 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8733. Min Act: 0.0000

Data Index: 676610 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1246240 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8326. Min Act: -0.0000

Data Index: 340979 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1417257 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7529. Min Act: -0.0000

Data Index: 282250 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7399. Min Act: -0.0000

Data Index: 950361 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1562075 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7084. Min Act: -0.0000

Data Index: 473385 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1879611 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1296821 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1065957 (The Pile)

Max Activating Token Index: 910

Text #13

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1614331 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1245963 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1827119 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1457470 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.6448. Min Act: -0.0000

Data Index: 726999 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.5766. Min Act: -0.0000

Data Index: 981774 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1718107 (The Pile)

Max Activating Token Index: 503