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

Dataset: The Pile

Neuron 265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1823626 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.3392. Min Act: -0.0000

Data Index: 397042 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.1272. Min Act: -0.0000

Data Index: 767187 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.1170. Min Act: -0.0000

Data Index: 339695 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1197395 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9795. Min Act: -0.0000

Data Index: 276222 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1080004 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1728486 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1709914 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1499856 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1875656 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9859. Min Act: -0.0000

Data Index: 376179 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1514758 (The Pile)

Max Activating Token Index: 725

Text #13

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.8986. Min Act: -0.0000

Data Index: 139884 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.3392. Min Range: -1.3392

Max Act: 1.0208. Min Act: -0.0000

Data Index: 550804 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1524644 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1022027 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9791. Min Act: -0.0000

Data Index: 920872 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9189. Min Act: -0.0000

Data Index: 515951 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 1.3392. Min Range: -1.3392

Max Act: 0.9186. Min Act: -0.0000

Data Index: 34185 (The Pile)

Max Activating Token Index: 12