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

Dataset: The Pile

Neuron 43 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1980836 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7803. Min Act: -0.0000

Data Index: 811313 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7805. Min Act: -0.0000

Data Index: 513185 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1212080 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1207732 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1133157 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6520. Min Act: -0.0000

Data Index: 787948 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6647. Min Act: -0.0000

Data Index: 666475 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1211248 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1807975 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1353479 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1689419 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1644717 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1619674 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1026632 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6347. Min Act: -0.0000

Data Index: 820451 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6600. Min Act: -0.0000

Data Index: 586248 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1698181 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1101183 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.5940. Min Act: -0.0000

Data Index: 918176 (The Pile)

Max Activating Token Index: 515