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

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

Neuron 3844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0707. Min Range: -1.0707

Max Act: 1.0707. Min Act: -0.0002

Data Index: 1521793 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9678. Min Act: -0.0002

Data Index: 1587200 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8497. Min Act: -0.0002

Data Index: 1391411 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8288. Min Act: -0.0002

Data Index: 1558049 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8492. Min Act: -0.0002

Data Index: 476193 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8296. Min Act: -0.0002

Data Index: 1649628 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7709. Min Act: -0.0002

Data Index: 209388 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7139. Min Act: -0.0002

Data Index: 404793 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8232. Min Act: -0.0002

Data Index: 270768 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7525. Min Act: -0.0002

Data Index: 1551113 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8597. Min Act: -0.0002

Data Index: 1226439 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7905. Min Act: -0.0002

Data Index: 620441 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8043. Min Act: -0.0002

Data Index: 1623864 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8178. Min Act: -0.0002

Data Index: 1409546 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7767. Min Act: -0.0002

Data Index: 1461867 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8446. Min Act: -0.0002

Data Index: 1484628 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7931. Min Act: -0.0002

Data Index: 1582345 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7073. Min Act: -0.0002

Data Index: 1451415 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7875. Min Act: -0.0002

Data Index: 1637098 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7900. Min Act: -0.0002

Data Index: 1651495 (Python Code)

Max Activating Token Index: 814