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

Dataset: The Pile

Neuron 3286 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1398637 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.4094. Min Act: -0.0000

Data Index: 498981 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.4151. Min Act: 0.0000

Data Index: 364767 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.3592. Min Act: -0.0000

Data Index: 552453 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2760. Min Act: -0.0000

Data Index: 680399 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1118512 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1953191 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1942874 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1032. Min Act: -0.0000

Data Index: 899267 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2158. Min Act: -0.0000

Data Index: 655689 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1276430 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1694848 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2405. Min Act: -0.0000

Data Index: 251908 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2694. Min Act: -0.0000

Data Index: 978607 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1693. Min Act: -0.0000

Data Index: 998992 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1862. Min Act: -0.0000

Data Index: 998923 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2606. Min Act: -0.0000

Data Index: 382340 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1182. Min Act: -0.0000

Data Index: 190285 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1598373 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1749. Min Act: -0.0000

Data Index: 383380 (The Pile)

Max Activating Token Index: 633