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

Dataset: The Pile

Neuron 5058 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: 3.0593. Min Range: -3.0593

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1752760 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 3.0593. Min Range: -3.0593

Max Act: 3.0219. Min Act: -0.0000

Data Index: 802241 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 3.0593. Min Range: -3.0593

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1695679 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1063696 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.9467. Min Act: -0.0000

Data Index: 26644 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.7035. Min Act: -0.0000

Data Index: 998362 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.5014. Min Act: -0.0000

Data Index: 81904 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3126. Min Act: -0.0000

Data Index: 1693225 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.4000. Min Act: -0.0000

Data Index: 791979 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3290. Min Act: -0.0000

Data Index: 693054 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.6455. Min Act: -0.0000

Data Index: 515233 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1977156 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.6474. Min Act: -0.0000

Data Index: 1502089 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.4872. Min Act: -0.0000

Data Index: 1323276 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.4765. Min Act: -0.0000

Data Index: 260151 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.5969. Min Act: -0.0000

Data Index: 1616083 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1195597 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1586674 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3484. Min Act: -0.0000

Data Index: 837709 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 3.0593. Min Range: -3.0593

Max Act: 2.3481. Min Act: -0.0000

Data Index: 623440 (The Pile)

Max Activating Token Index: 6