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

Dataset: The Pile

Neuron 3502 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0000

Data Index: 629412 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1001459 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0155. Min Act: -0.0000

Data Index: 666209 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8616. Min Act: -0.0000

Data Index: 961508 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1114202 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1658490 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8444. Min Act: -0.0000

Data Index: 47443 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0136. Min Act: -0.0000

Data Index: 873398 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1438409 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1108509 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8918. Min Act: -0.0000

Data Index: 674200 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1459776 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8418. Min Act: -0.0000

Data Index: 207508 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1063053 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1560420 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7657. Min Act: -0.0000

Data Index: 36012 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1108371 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8211. Min Act: -0.0000

Data Index: 365769 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1071113 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7667. Min Act: -0.0000

Data Index: 720454 (The Pile)

Max Activating Token Index: 805