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

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

Neuron 118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1423506 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1920. Min Act: -0.0000

Data Index: 262511 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1508214 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1443567 (Python Code)

Max Activating Token Index: 742

Text #4

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1438276 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1620. Min Act: -0.0000

Data Index: 593387 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1640503 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1500. Min Act: -0.0001

Data Index: 837137 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1479. Min Act: -0.0000

Data Index: 844986 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1364. Min Act: -0.0000

Data Index: 488568 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1462332 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1514144 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1382. Min Act: -0.0001

Data Index: 170717 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1388. Min Act: -0.0000

Data Index: 280707 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1634979 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1589803 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1550724 (Python Code)

Max Activating Token Index: 781

Text #17

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1510363 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1387. Min Act: -0.0001

Data Index: 561972 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1920. Min Range: -0.1920

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1612562 (Python Code)

Max Activating Token Index: 557