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

Dataset: The Pile

Neuron 1878 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.2586. Min Act: -0.0000

Data Index: 571460 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.1759. Min Act: -0.0000

Data Index: 245897 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1471609 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1676713 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1341848 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.0250. Min Act: -0.0000

Data Index: 456928 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1542557 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8931. Min Act: -0.0000

Data Index: 201775 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8597. Min Act: -0.0000

Data Index: 941953 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9116. Min Act: -0.0000

Data Index: 502090 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8930. Min Act: -0.0000

Data Index: 453392 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8863. Min Act: -0.0000

Data Index: 990700 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1259569 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8773. Min Act: -0.0000

Data Index: 874482 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8593. Min Act: -0.0000

Data Index: 363513 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1018113 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1788274 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1339661 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9123. Min Act: -0.0000

Data Index: 533730 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8584. Min Act: -0.0000

Data Index: 426373 (The Pile)

Max Activating Token Index: 143