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

Dataset: The Pile

Neuron 1575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1200005 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0000

Data Index: 419135 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4230. Min Act: -0.0000

Data Index: 650798 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4396. Min Act: -0.0000

Data Index: 579407 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3923. Min Act: -0.0000

Data Index: 58782 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1806536 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1335258 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3756. Min Act: -0.0000

Data Index: 376287 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1517075 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3728. Min Act: -0.0000

Data Index: 275550 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1871986 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3692. Min Act: -0.0000

Data Index: 480452 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3783. Min Act: -0.0000

Data Index: 180009 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3610. Min Act: -0.0000

Data Index: 391700 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1367407 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1663633 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3428. Min Act: -0.0000

Data Index: 14880 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1933220 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3736. Min Act: -0.0000

Data Index: 959096 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3402. Min Act: -0.0000

Data Index: 331586 (The Pile)

Max Activating Token Index: 733