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

Dataset: The Pile

Neuron 1064 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: 0.3402. Min Range: -0.3402

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1984863 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3172. Min Act: -0.0000

Data Index: 444297 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1478488 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1043697 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2816. Min Act: -0.0000

Data Index: 67256 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1424584 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2389. Min Act: -0.0000

Data Index: 781723 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2516. Min Act: 0.0000

Data Index: 953139 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1335748 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2357. Min Act: -0.0000

Data Index: 534515 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2214. Min Act: -0.0000

Data Index: 752461 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1431092 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1655750 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.1969. Min Act: -0.0000

Data Index: 218362 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1498750 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2159. Min Act: -0.0000

Data Index: 703589 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2218. Min Act: -0.0000

Data Index: 459979 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1407480 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2131. Min Act: -0.0000

Data Index: 232107 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1346453 (The Pile)

Max Activating Token Index: 938