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

Dataset: The Pile

Neuron 3359 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: 1.1397. Min Range: -1.1397

Max Act: 1.1397. Min Act: -0.0000

Data Index: 863443 (The Pile)

Max Activating Token Index: 825

Text #1

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9789. Min Act: -0.0000

Data Index: 349877 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9848. Min Act: -0.0000

Data Index: 727726 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1103931 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8535. Min Act: -0.0000

Data Index: 629325 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9200. Min Act: -0.0000

Data Index: 703571 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1535971 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1518 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1480043 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1737309 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1563864 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8099. Min Act: -0.0000

Data Index: 936303 (The Pile)

Max Activating Token Index: 784

Text #12

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1160402 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1014923 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1785355 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1802482 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7513. Min Act: -0.0000

Data Index: 628146 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8358. Min Act: -0.0000

Data Index: 384883 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1545841 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1130891 (The Pile)

Max Activating Token Index: 781