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

Dataset: The Pile

Neuron 843 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1842. Min Range: -11.1842

Max Act: 11.1842. Min Act: -0.0000

Data Index: 1012069 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.4729. Min Act: -0.0000

Data Index: 1590827 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.5061. Min Act: -0.0000

Data Index: 280980 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.1991. Min Act: -0.0000

Data Index: 1768574 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.5557. Min Act: -0.0000

Data Index: 643194 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.2809. Min Act: -0.0000

Data Index: 580385 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.4219. Min Act: -0.0000

Data Index: 129220 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.6849. Min Act: -0.0000

Data Index: 1803389 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.6574. Min Act: -0.0000

Data Index: 153198 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.1533. Min Act: -0.0000

Data Index: 796423 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.9550. Min Act: -0.0000

Data Index: 1677959 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 11.1842. Min Range: -11.1842

Max Act: 10.0846. Min Act: -0.0000

Data Index: 1547179 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.7869. Min Act: -0.0000

Data Index: 1960461 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.5652. Min Act: -0.0000

Data Index: 1699446 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.8518. Min Act: -0.0000

Data Index: 788100 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.7899. Min Act: -0.0000

Data Index: 1269005 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.8077. Min Act: -0.0000

Data Index: 680137 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.6281. Min Act: -0.0000

Data Index: 812261 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.5451. Min Act: -0.0000

Data Index: 1742999 (The Pile)

Max Activating Token Index: 174

Text #19

Max Range: 11.1842. Min Range: -11.1842

Max Act: 9.8568. Min Act: -0.0000

Data Index: 1771265 (The Pile)

Max Activating Token Index: 525