Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 731 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9272. Min Act: -0.0000

Data Index: 61559 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1698783 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8755. Min Act: -0.0000

Data Index: 573844 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1179290 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9494. Min Act: -0.0000

Data Index: 249160 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1175190 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1965760 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1594622 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1584888 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7722. Min Act: -0.0000

Data Index: 991931 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8154. Min Act: -0.0000

Data Index: 243310 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8680. Min Act: -0.0000

Data Index: 120652 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8699. Min Act: -0.0000

Data Index: 109382 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1877493 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1456168 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8604. Min Act: -0.0000

Data Index: 648410 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1864591 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1558392 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8087. Min Act: -0.0000

Data Index: 552253 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8196. Min Act: -0.0000

Data Index: 348913 (The Pile)

Max Activating Token Index: 192