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

Dataset: The Pile

Neuron 2481 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2401. Min Act: -0.0000

Data Index: 1296697 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.6526. Min Act: -0.0000

Data Index: 1028352 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.4557. Min Act: -0.0000

Data Index: 314711 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.4632. Min Act: -0.0000

Data Index: 518588 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.3612. Min Act: -0.0000

Data Index: 991548 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.4179. Min Act: -0.0000

Data Index: 145317 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2978. Min Act: -0.0000

Data Index: 1419113 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.4553. Min Act: -0.0000

Data Index: 1899488 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1264169 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.1709. Min Act: -0.0000

Data Index: 1081772 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.1402. Min Act: -0.0000

Data Index: 439647 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.1691. Min Act: -0.0000

Data Index: 1671108 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.3322. Min Act: -0.0000

Data Index: 537955 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2105. Min Act: -0.0000

Data Index: 1269444 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2934. Min Act: -0.0000

Data Index: 38428 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2721. Min Act: -0.0000

Data Index: 1599964 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.2416. Min Act: -0.0000

Data Index: 234198 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 3.6526. Min Range: -3.6526

Max Act: 3.0410. Min Act: -0.0000

Data Index: 1828598 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 3.6526. Min Range: -3.6526

Max Act: 2.9339. Min Act: -0.0000

Data Index: 592550 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 3.6526. Min Range: -3.6526

Max Act: 2.8875. Min Act: -0.0000

Data Index: 93586 (The Pile)

Max Activating Token Index: 585