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

Dataset: The Pile

Neuron 2132 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: 5.1455. Min Range: -5.1455

Max Act: 5.1455. Min Act: -0.0000

Data Index: 80768 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.1955. Min Act: -0.0000

Data Index: 423099 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.2769. Min Act: -0.0000

Data Index: 857922 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.5679. Min Act: -0.0000

Data Index: 520555 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.9300. Min Act: -0.0000

Data Index: 544571 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.0063. Min Act: -0.0000

Data Index: 421203 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.1379. Min Act: -0.0000

Data Index: 1202508 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.1679. Min Act: -0.0000

Data Index: 267354 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.2923. Min Act: -0.0000

Data Index: 1349733 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9420. Min Act: -0.0000

Data Index: 781570 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9359. Min Act: -0.0000

Data Index: 657892 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9380. Min Act: -0.0000

Data Index: 36867 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9290. Min Act: -0.0000

Data Index: 225801 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 5.1455. Min Range: -5.1455

Max Act: 3.0381. Min Act: -0.0000

Data Index: 220856 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9256. Min Act: 0.0001

Data Index: 754975 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.9234. Min Act: -0.0000

Data Index: 496674 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.7769. Min Act: -0.0000

Data Index: 1080776 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.7106. Min Act: -0.0000

Data Index: 649502 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.8080. Min Act: -0.0000

Data Index: 1748640 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 5.1455. Min Range: -5.1455

Max Act: 2.6380. Min Act: -0.0000

Data Index: 41203 (The Pile)

Max Activating Token Index: 253