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

Dataset: The Pile

Neuron 683 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: 1.5555. Min Range: -1.5555

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1447077 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1586. Min Act: -0.0000

Data Index: 339314 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1311705 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1842397 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1753. Min Act: -0.0000

Data Index: 575394 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2208. Min Act: -0.0000

Data Index: 906336 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.3008. Min Act: -0.0000

Data Index: 34203 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.4008. Min Act: -0.0000

Data Index: 672895 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2774. Min Act: -0.0000

Data Index: 838157 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2120. Min Act: -0.0000

Data Index: 188848 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2252. Min Act: -0.0000

Data Index: 397820 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2033. Min Act: -0.0000

Data Index: 179375 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1056049 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1155. Min Act: -0.0000

Data Index: 137667 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1430. Min Act: -0.0000

Data Index: 607457 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2228. Min Act: -0.0000

Data Index: 897290 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1634903 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2556. Min Act: -0.0000

Data Index: 102947 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1256842 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1575194 (The Pile)

Max Activating Token Index: 718