Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.9168. Min Act: -0.0000

Data Index: 796589 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7761. Min Act: -0.0000

Data Index: 999530 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1360487 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1316103 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6963. Min Act: -0.0000

Data Index: 687124 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1186199 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6377. Min Act: -0.0000

Data Index: 66420 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1103550 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6190. Min Act: -0.0000

Data Index: 714064 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6480. Min Act: -0.0001

Data Index: 1510126 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1111330 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1699326 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1360643 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5811. Min Act: -0.0000

Data Index: 242155 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1281406 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5811. Min Act: -0.0001

Data Index: 976584 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5741. Min Act: -0.0000

Data Index: 505802 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1902454 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5621. Min Act: -0.0001

Data Index: 493135 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1925206 (The Pile)

Max Activating Token Index: 1009