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

Dataset: The Pile

Neuron 40 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: 0.4679. Min Range: -0.4679

Max Act: 0.4679. Min Act: -0.0000

Data Index: 560402 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1361808 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1013403 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1438038 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1178164 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1011554 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1616579 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3082. Min Act: -0.0000

Data Index: 947639 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1442343 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1627182 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2650. Min Act: -0.0000

Data Index: 321590 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1197399 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1763709 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2738. Min Act: -0.0000

Data Index: 953740 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2814. Min Act: -0.0000

Data Index: 485615 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1055079 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2399. Min Act: -0.0000

Data Index: 798618 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1896521 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2694. Min Act: -0.0000

Data Index: 835190 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1752891 (The Pile)

Max Activating Token Index: 710