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

Dataset: The Pile

Neuron 3138 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.2517. Min Range: -11.2517

Max Act: 11.2517. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 11.2517. Min Range: -11.2517

Max Act: 11.1642. Min Act: -0.0000

Data Index: 24806 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.5795. Min Act: -0.0000

Data Index: 1992689 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.2967. Min Act: -0.0000

Data Index: 202335 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.9479. Min Act: -0.0000

Data Index: 1389421 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.7152. Min Act: -0.0000

Data Index: 830196 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.9527. Min Act: -0.0000

Data Index: 1556144 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.0242. Min Act: -0.0000

Data Index: 1845979 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.2193. Min Act: -0.0000

Data Index: 1206086 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.8416. Min Act: -0.0000

Data Index: 1431192 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 11.2517. Min Range: -11.2517

Max Act: 10.2811. Min Act: -0.0000

Data Index: 1254359 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.3492. Min Act: -0.0000

Data Index: 1192363 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.6207. Min Act: -0.0000

Data Index: 511315 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.1051. Min Act: -0.0000

Data Index: 508401 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.5203. Min Act: -0.0000

Data Index: 1128833 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.5119. Min Act: -0.0000

Data Index: 569473 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.1873. Min Act: -0.0000

Data Index: 1263491 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.4756. Min Act: -0.0000

Data Index: 883783 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.1021. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 11.2517. Min Range: -11.2517

Max Act: 9.1241. Min Act: -0.0000

Data Index: 1682566 (The Pile)

Max Activating Token Index: 318