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

Dataset: The Pile

Neuron 3294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.9812. Min Act: -0.0000

Data Index: 1711605 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.7977. Min Act: -0.0000

Data Index: 919081 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.1925. Min Act: -0.0000

Data Index: 614302 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.2208. Min Act: -0.0000

Data Index: 976263 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.4169. Min Act: -0.0000

Data Index: 1312236 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.1698. Min Act: -0.0000

Data Index: 1535191 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.0472. Min Act: -0.0000

Data Index: 862436 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 3.9812. Min Range: -3.9812

Max Act: 3.1177. Min Act: -0.0000

Data Index: 441952 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.6458. Min Act: -0.0000

Data Index: 54625 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.6856. Min Act: -0.0000

Data Index: 1739596 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5356. Min Act: -0.0000

Data Index: 1479490 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.6335. Min Act: -0.0000

Data Index: 477421 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.6273. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5919. Min Act: -0.0000

Data Index: 523091 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5812. Min Act: -0.0000

Data Index: 878456 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5647. Min Act: -0.0000

Data Index: 1046481 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5597. Min Act: -0.0000

Data Index: 169526 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5671. Min Act: -0.0000

Data Index: 128968 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.4146. Min Act: -0.0000

Data Index: 1625937 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 3.9812. Min Range: -3.9812

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1488850 (The Pile)

Max Activating Token Index: 165