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

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

Neuron 2028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0001

Data Index: 803209 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1826. Min Act: -0.0001

Data Index: 676981 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1737. Min Act: -0.0000

Data Index: 418691 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1612. Min Act: -0.0001

Data Index: 452277 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1500545 (Python Code)

Max Activating Token Index: 391

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1586. Min Act: -0.0001

Data Index: 81020 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1089946 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1389. Min Act: -0.0001

Data Index: 940719 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1467001 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1209865 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1355. Min Act: -0.0000

Data Index: 525610 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1401. Min Act: -0.0000

Data Index: 380792 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1293. Min Act: -0.0001

Data Index: 802564 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1404. Min Act: -0.0001

Data Index: 824855 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1337. Min Act: -0.0001

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1304. Min Act: -0.0000

Data Index: 585836 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1082639 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1368. Min Act: -0.0000

Data Index: 955055 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1318. Min Act: -0.0000

Data Index: 510562 (C4 (Web Text))

Max Activating Token Index: 181