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

Dataset: The Pile

Neuron 3259 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: 1.9576. Min Range: -1.9576

Max Act: 1.9576. Min Act: -0.0000

Data Index: 849257 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1741466 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3307. Min Act: -0.0000

Data Index: 802976 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1226122 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3130. Min Act: -0.0000

Data Index: 4749 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1320290 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3730. Min Act: -0.0000

Data Index: 1502919 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2829. Min Act: -0.0000

Data Index: 696444 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1727245 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1415404 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1950110 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1195659 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2227. Min Act: -0.0000

Data Index: 365075 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.1998. Min Act: -0.0000

Data Index: 743505 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2617. Min Act: -0.0000

Data Index: 969060 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1619321 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.1726. Min Act: -0.0000

Data Index: 125114 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1031429 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.1702. Min Act: -0.0000

Data Index: 405689 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2732. Min Act: -0.0000

Data Index: 269163 (The Pile)

Max Activating Token Index: 399