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

Dataset: The Pile

Neuron 2197 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: 0.8319. Min Range: -0.8319

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1689043 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1185248 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6296. Min Act: -0.0000

Data Index: 160370 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5753. Min Act: -0.0000

Data Index: 919733 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1616858 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5897. Min Act: -0.0000

Data Index: 329284 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6028. Min Act: -0.0000

Data Index: 212119 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5267. Min Act: -0.0000

Data Index: 890656 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1348842 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1630173 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1253426 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5015. Min Act: -0.0000

Data Index: 976301 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1209535 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4814. Min Act: -0.0000

Data Index: 948097 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4726. Min Act: -0.0000

Data Index: 521251 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1761907 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4665. Min Act: -0.0000

Data Index: 480754 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4448. Min Act: -0.0000

Data Index: 380287 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1522623 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1364773 (The Pile)

Max Activating Token Index: 941