Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 249 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0003

Data Index: 895096 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0737. Min Act: -0.0003

Data Index: 380793 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0680. Min Act: -0.0001

Data Index: 917704 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1423486 (Python Code)

Max Activating Token Index: 801

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1596306 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1464879 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1621222 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0634. Min Act: -0.0003

Data Index: 505833 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0648. Min Act: -0.0003

Data Index: 900356 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1417760 (Python Code)

Max Activating Token Index: 466

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1458160 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0636. Min Act: -0.0003

Data Index: 417861 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1475999 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0633. Min Act: -0.0003

Data Index: 341987 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1190402 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0637. Min Act: -0.0003

Data Index: 138773 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0630. Min Act: -0.0003

Data Index: 754559 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1617488 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1655561 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0612. Min Act: -0.0002

Data Index: 282931 (C4 (Web Text))

Max Activating Token Index: 652