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

Dataset: The Pile

Neuron 655 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: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1300540 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1557438 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1828. Min Act: -0.0000

Data Index: 385432 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1852. Min Act: -0.0000

Data Index: 883809 (The Pile)

Max Activating Token Index: 566

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1710. Min Act: -0.0000

Data Index: 696156 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1706. Min Act: -0.0000

Data Index: 190435 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1054083 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1393807 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1823431 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1582. Min Act: -0.0000

Data Index: 775724 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1488948 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1044168 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1593. Min Act: -0.0000

Data Index: 943867 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1707. Min Act: -0.0000

Data Index: 744157 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1622. Min Act: -0.0000

Data Index: 77027 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1535. Min Act: -0.0000

Data Index: 508902 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1645452 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1897701 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1406. Min Act: -0.0000

Data Index: 999388 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1497. Min Act: -0.0000

Data Index: 712940 (The Pile)

Max Activating Token Index: 889