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

Dataset: The Pile

Neuron 1519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0000

Data Index: 969456 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9315. Min Act: -0.0000

Data Index: 330910 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1394. Min Act: -0.0000

Data Index: 717357 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1521089 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0063. Min Act: -0.0000

Data Index: 62446 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1925506 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9340. Min Act: -0.0000

Data Index: 911665 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1845850 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1656291 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8784. Min Act: -0.0000

Data Index: 923631 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1357640 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1750821 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9771. Min Act: -0.0000

Data Index: 391839 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9202. Min Act: -0.0000

Data Index: 275639 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1225291 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8974. Min Act: -0.0000

Data Index: 11210 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1439686 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8948. Min Act: -0.0000

Data Index: 124133 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1663783 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1047350 (The Pile)

Max Activating Token Index: 329