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

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

Neuron 3698 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1224593 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1987. Min Act: -0.0001

Data Index: 591780 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1923. Min Act: -0.0001

Data Index: 317741 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1820. Min Act: -0.0001

Data Index: 43874 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1206055 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1890. Min Act: -0.0001

Data Index: 543746 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1755. Min Act: -0.0001

Data Index: 588022 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1017955 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1743. Min Act: -0.0001

Data Index: 215662 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1842. Min Act: -0.0001

Data Index: 568688 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1084337 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1043904 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1032020 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1670. Min Act: -0.0001

Data Index: 285084 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1669. Min Act: -0.0001

Data Index: 664098 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1057324 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1594. Min Act: -0.0001

Data Index: 635076 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1619. Min Act: -0.0001

Data Index: 703504 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1604. Min Act: -0.0001

Data Index: 60905 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1348407 (C4 (Web Text))

Max Activating Token Index: 221