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

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

Neuron 4967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1742. Min Act: -0.0000

Data Index: 473893 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1728. Min Act: -0.0000

Data Index: 939465 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1131422 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1716. Min Act: -0.0000

Data Index: 811232 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1097507 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1206188 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1016989 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1667. Min Act: -0.0000

Data Index: 541253 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1655. Min Act: -0.0000

Data Index: 100260 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1632. Min Act: -0.0000

Data Index: 677248 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1440. Min Act: -0.0000

Data Index: 82594 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1470. Min Act: -0.0000

Data Index: 571914 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1418. Min Act: -0.0000

Data Index: 292939 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1394. Min Act: -0.0000

Data Index: 893806 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1341. Min Act: -0.0000

Data Index: 261842 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1304. Min Act: -0.0000

Data Index: 995583 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1337. Min Act: -0.0000

Data Index: 439721 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1337. Min Act: -0.0000

Data Index: 67844 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1454. Min Act: -0.0000

Data Index: 620040 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1374. Min Act: -0.0000

Data Index: 398965 (C4 (Web Text))

Max Activating Token Index: 584