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

Dataset: The Pile

Neuron 1198 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: 0.7317. Min Range: -0.7317

Max Act: 0.7317. Min Act: -0.0000

Data Index: 704779 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1467925 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1945361 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1390339 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4838. Min Act: -0.0000

Data Index: 968284 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4469. Min Act: -0.0000

Data Index: 55465 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4961. Min Act: -0.0000

Data Index: 572488 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1966052 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4053. Min Act: -0.0000

Data Index: 443651 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1071085 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.3370. Min Act: -0.0000

Data Index: 434769 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1301746 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4204. Min Act: -0.0000

Data Index: 68561 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4446. Min Act: -0.0000

Data Index: 572053 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.3710. Min Act: -0.0000

Data Index: 243171 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4433. Min Act: -0.0000

Data Index: 949967 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1446334 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1916026 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1841502 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1570715 (The Pile)

Max Activating Token Index: 201