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

Dataset: The Pile

Neuron 2034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.7458. Min Act: -0.0000

Data Index: 1436140 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6242. Min Act: -0.0000

Data Index: 376493 (The Pile)

Max Activating Token Index: 319

Text #2

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.7883. Min Act: -0.0000

Data Index: 1188580 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.9480. Min Act: -0.0000

Data Index: 487410 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.4031. Min Act: -0.0000

Data Index: 96754 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.3436. Min Act: -0.0000

Data Index: 668219 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.4675. Min Act: -0.0000

Data Index: 1222378 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.2504. Min Act: 0.0000

Data Index: 1980724 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.1647. Min Act: 0.0000

Data Index: 1332111 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.4566. Min Act: -0.0000

Data Index: 1731552 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.3594. Min Act: -0.0000

Data Index: 1768662 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.0371. Min Act: -0.0000

Data Index: 1941385 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.1282. Min Act: -0.0000

Data Index: 644629 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.1089. Min Act: -0.0000

Data Index: 1634193 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.1672. Min Act: -0.0000

Data Index: 854165 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 3.9480. Min Range: -3.9480

Max Act: 2.9701. Min Act: -0.0000

Data Index: 1827643 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.0546. Min Act: -0.0000

Data Index: 152215 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 3.9480. Min Range: -3.9480

Max Act: 2.9163. Min Act: 0.0000

Data Index: 1963487 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 3.9480. Min Range: -3.9480

Max Act: 2.8292. Min Act: -0.0000

Data Index: 1365149 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 3.9480. Min Range: -3.9480

Max Act: 2.9064. Min Act: 0.0000

Data Index: 382883 (The Pile)

Max Activating Token Index: 620