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

Dataset: The Pile

Neuron 1070 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: 1.7407. Min Range: -1.7407

Max Act: 1.7407. Min Act: -0.0000

Data Index: 76968 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.5268. Min Act: -0.0000

Data Index: 842250 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.4508. Min Act: -0.0000

Data Index: 226339 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1149400 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1877003 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1098740 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1711. Min Act: -0.0000

Data Index: 582843 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3105. Min Act: -0.0000

Data Index: 886850 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2242. Min Act: -0.0000

Data Index: 689157 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1935974 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1429. Min Act: -0.0000

Data Index: 390499 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1230854 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1311085 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1481348 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1626167 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1031. Min Act: -0.0000

Data Index: 369190 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2300. Min Act: -0.0000

Data Index: 828179 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1930378 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0716. Min Act: -0.0000

Data Index: 664082 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1943487 (The Pile)

Max Activating Token Index: 872