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

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

Neuron 1762 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 106821 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0652. Min Act: -0.0002

Data Index: 766264 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0609. Min Act: -0.0001

Data Index: 885090 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0606. Min Act: -0.0001

Data Index: 656251 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0599. Min Act: -0.0001

Data Index: 197493 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0600. Min Act: -0.0001

Data Index: 867549 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0574. Min Act: -0.0002

Data Index: 263193 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0589. Min Act: -0.0002

Data Index: 533969 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0534. Min Act: -0.0002

Data Index: 929755 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0542. Min Act: -0.0001

Data Index: 379920 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0574. Min Act: -0.0001

Data Index: 864345 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0517. Min Act: -0.0001

Data Index: 587583 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0527. Min Act: -0.0002

Data Index: 999538 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0574. Min Act: -0.0001

Data Index: 607994 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1208984 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0537. Min Act: -0.0001

Data Index: 379668 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1303890 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0498. Min Act: -0.0002

Data Index: 614951 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0505. Min Act: -0.0002

Data Index: 360729 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1169798 (C4 (Web Text))

Max Activating Token Index: 184