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

Dataset: The Pile

Neuron 1170 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: 1.4179. Min Range: -1.4179

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1461997 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1909650 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2031. Min Act: -0.0000

Data Index: 610635 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1583. Min Act: -0.0000

Data Index: 725378 (The Pile)

Max Activating Token Index: 705

Text #4

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1475476 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1312648 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1712. Min Act: -0.0000

Data Index: 12846 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1847902 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2963. Min Act: -0.0000

Data Index: 178229 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1267349 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0237. Min Act: -0.0000

Data Index: 523456 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1461552 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1199814 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1818009 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1804. Min Act: -0.0000

Data Index: 877754 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1559. Min Act: -0.0000

Data Index: 536798 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1627116 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1793260 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1438. Min Act: -0.0000

Data Index: 357054 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0765. Min Act: -0.0000

Data Index: 231766 (The Pile)

Max Activating Token Index: 638