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

Dataset: The Pile

Neuron 4011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.7089. Min Act: -0.0000

Data Index: 1813254 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3949. Min Act: -0.0000

Data Index: 240390 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1183510 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3151. Min Act: -0.0000

Data Index: 509823 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1970272 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3574. Min Act: -0.0000

Data Index: 237405 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1437925 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3437. Min Act: -0.0000

Data Index: 543772 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1134888 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.2247. Min Act: -0.0000

Data Index: 914079 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1355795 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.2860. Min Act: -0.0000

Data Index: 29880 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1271339 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1973. Min Act: -0.0000

Data Index: 890346 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.2190. Min Act: -0.0000

Data Index: 159893 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1139816 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1424456 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1370009 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1194. Min Act: -0.0000

Data Index: 381315 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.7089. Min Range: -1.7089

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1859877 (The Pile)

Max Activating Token Index: 29