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

Dataset: The Pile

Neuron 1643 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: 0.6589. Min Range: -0.6589

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1315035 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1407614 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1226798 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5899. Min Act: -0.0000

Data Index: 362367 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1573410 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5146. Min Act: -0.0000

Data Index: 750747 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5141. Min Act: -0.0000

Data Index: 344531 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4559. Min Act: -0.0000

Data Index: 20795 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4998. Min Act: -0.0000

Data Index: 56363 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4742. Min Act: -0.0000

Data Index: 90572 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4520. Min Act: -0.0000

Data Index: 148543 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5057. Min Act: -0.0000

Data Index: 942651 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4043. Min Act: -0.0000

Data Index: 914520 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5162. Min Act: -0.0000

Data Index: 546563 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4655. Min Act: -0.0000

Data Index: 30257 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5075. Min Act: -0.0000

Data Index: 933446 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5394. Min Act: -0.0000

Data Index: 418170 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4037. Min Act: -0.0000

Data Index: 35821 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4377. Min Act: -0.0000

Data Index: 725920 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1400867 (The Pile)

Max Activating Token Index: 230