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

Dataset: The Pile

Neuron 3364 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: 0.6357. Min Range: -0.6357

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1922364 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5578. Min Act: -0.0000

Data Index: 911034 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1417267 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5344. Min Act: -0.0000

Data Index: 947372 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1735434 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5184. Min Act: -0.0000

Data Index: 376761 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4629. Min Act: -0.0000

Data Index: 456540 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5261. Min Act: -0.0000

Data Index: 242088 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.5013. Min Act: -0.0000

Data Index: 157602 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1594752 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4873. Min Act: -0.0000

Data Index: 674817 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4672. Min Act: -0.0000

Data Index: 444295 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4567. Min Act: -0.0000

Data Index: 290522 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4469. Min Act: -0.0000

Data Index: 439355 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1226302 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1071528 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4908. Min Act: -0.0000

Data Index: 322322 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4441. Min Act: -0.0000

Data Index: 726097 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4453. Min Act: -0.0000

Data Index: 337983 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 0.6357. Min Range: -0.6357

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1412817 (The Pile)

Max Activating Token Index: 648