Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 969 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0001

Data Index: 173318 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0670. Min Act: -0.0001

Data Index: 320433 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0619. Min Act: -0.0001

Data Index: 691732 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0606. Min Act: -0.0001

Data Index: 464731 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0607. Min Act: -0.0001

Data Index: 481594 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0545. Min Act: -0.0001

Data Index: 220608 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0575. Min Act: -0.0001

Data Index: 943107 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0517. Min Act: -0.0001

Data Index: 529947 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0510. Min Act: -0.0001

Data Index: 593061 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1170104 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0513. Min Act: -0.0001

Data Index: 767583 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1327944 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0461. Min Act: -0.0001

Data Index: 388181 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0497. Min Act: -0.0001

Data Index: 37777 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1206077 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0466. Min Act: -0.0001

Data Index: 830391 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1128246 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0438. Min Act: -0.0001

Data Index: 98723 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0412. Min Act: -0.0001

Data Index: 827287 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0441. Min Act: -0.0001

Data Index: 627290 (C4 (Web Text))

Max Activating Token Index: 134