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

Dataset: The Pile

Neuron 873 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: 0.8222. Min Range: -0.8222

Max Act: 0.8222. Min Act: -0.0000

Data Index: 610299 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1443641 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1073565 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6993. Min Act: -0.0000

Data Index: 601369 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6726. Min Act: -0.0000

Data Index: 649933 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1150162 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6717. Min Act: -0.0000

Data Index: 252568 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6903. Min Act: -0.0000

Data Index: 312670 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6651. Min Act: -0.0000

Data Index: 268031 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6601. Min Act: -0.0000

Data Index: 735446 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6516. Min Act: -0.0000

Data Index: 476585 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1383241 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6084. Min Act: -0.0000

Data Index: 305011 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1613433 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1862309 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1724294 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5883. Min Act: -0.0000

Data Index: 290 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1844974 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1429782 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5961. Min Act: -0.0000

Data Index: 638236 (The Pile)

Max Activating Token Index: 13