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

Dataset: The Pile

Neuron 1353 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: 0.7559. Min Act: -0.0000

Data Index: 148273 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.8222. Min Act: -0.0000

Data Index: 967025 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6863. Min Act: -0.0000

Data Index: 469805 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6913. Min Act: -0.0000

Data Index: 276119 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1250392 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6414. Min Act: -0.0000

Data Index: 884438 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6761. Min Act: -0.0000

Data Index: 838288 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1198361 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1278425 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1269584 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6922. Min Act: -0.0000

Data Index: 14233 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7154. Min Act: -0.0000

Data Index: 539636 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6170. Min Act: -0.0000

Data Index: 251019 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1248769 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6605. Min Act: -0.0000

Data Index: 307752 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6977. Min Act: -0.0000

Data Index: 391008 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1131015 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1408417 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1822724 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1916935 (The Pile)

Max Activating Token Index: 65