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

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

Neuron 1296 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: 0.1666. Min Range: -0.1666

Max Act: 0.1666. Min Act: -0.0000

Data Index: 241205 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1529. Min Act: -0.0000

Data Index: 5437 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1542. Min Act: -0.0001

Data Index: 634269 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1471. Min Act: -0.0000

Data Index: 149346 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1522. Min Act: -0.0001

Data Index: 169165 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1562. Min Act: -0.0000

Data Index: 730932 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1515. Min Act: -0.0000

Data Index: 801259 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1196889 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1449. Min Act: 0.0000

Data Index: 104686 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1008668 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1499. Min Act: -0.0000

Data Index: 737471 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1381. Min Act: -0.0000

Data Index: 36090 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1359. Min Act: -0.0000

Data Index: 265226 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1179337 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1092202 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1447. Min Act: -0.0000

Data Index: 924740 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1388. Min Act: -0.0000

Data Index: 869267 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1105833 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1385. Min Act: -0.0000

Data Index: 783623 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1385. Min Act: -0.0000

Data Index: 781928 (C4 (Web Text))

Max Activating Token Index: 845