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

Dataset: The Pile

Neuron 1430 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.3233. Min Act: -0.0000

Data Index: 1075058 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.1856. Min Act: -0.0000

Data Index: 200348 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.9429. Min Act: -0.0000

Data Index: 1636657 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.2999. Min Act: -0.0000

Data Index: 1533443 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.1084. Min Act: -0.0000

Data Index: 358422 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.0733. Min Act: -0.0000

Data Index: 921422 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.0418. Min Act: -0.0000

Data Index: 1240210 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.0541. Min Act: -0.0000

Data Index: 1007532 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.8046. Min Act: -0.0000

Data Index: 1836802 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.9878. Min Act: -0.0000

Data Index: 83535 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.8044. Min Act: -0.0000

Data Index: 209600 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.0421. Min Act: -0.0000

Data Index: 1590212 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.0272. Min Act: -0.0000

Data Index: 521563 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.4412. Min Act: -0.0000

Data Index: 106327 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 4.4412. Min Range: -4.4412

Max Act: 4.1942. Min Act: -0.0000

Data Index: 1885061 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.6498. Min Act: -0.0000

Data Index: 90787 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.5676. Min Act: -0.0000

Data Index: 264601 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.6124. Min Act: -0.0000

Data Index: 590489 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.3834. Min Act: -0.0000

Data Index: 869608 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 4.4412. Min Range: -4.4412

Max Act: 3.5635. Min Act: -0.0000

Data Index: 1478253 (The Pile)

Max Activating Token Index: 312