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

Dataset: The Pile

Neuron 569 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: 2.2446. Min Range: -2.2446

Max Act: 2.1690. Min Act: -0.0000

Data Index: 386974 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2446. Min Act: -0.0000

Data Index: 644931 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7740. Min Act: -0.0000

Data Index: 717306 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.6735. Min Act: -0.0000

Data Index: 398784 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1334036 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.5851. Min Act: -0.0000

Data Index: 378017 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1973894 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.6091. Min Act: -0.0000

Data Index: 447485 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1661624 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1405649 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1459312 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1319745 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7257. Min Act: -0.0000

Data Index: 1240858 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.6117. Min Act: -0.0000

Data Index: 344780 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1125124 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.6239. Min Act: -0.0000

Data Index: 291409 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.5847. Min Act: -0.0000

Data Index: 991630 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1209889 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.5626. Min Act: -0.0000

Data Index: 264730 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 2.2446. Min Range: -2.2446

Max Act: 1.7656. Min Act: -0.0000

Data Index: 999720 (The Pile)

Max Activating Token Index: 349