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

Dataset: The Pile

Neuron 58 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: 1.4164. Min Range: -1.4164

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1374920 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1170711 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1327992 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1664367 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1910483 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1251834 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1228546 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.3244. Min Act: -0.0000

Data Index: 356555 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1700949 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1679. Min Act: -0.0000

Data Index: 418603 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0429. Min Act: -0.0000

Data Index: 822029 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2617. Min Act: -0.0000

Data Index: 61057 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0639. Min Act: -0.0001

Data Index: 162370 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9990. Min Act: -0.0000

Data Index: 251831 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1076. Min Act: -0.0000

Data Index: 322129 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2044. Min Act: -0.0000

Data Index: 972244 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0206. Min Act: -0.0000

Data Index: 56289 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.8916. Min Act: -0.0000

Data Index: 805472 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1999959 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1716821 (The Pile)

Max Activating Token Index: 1018