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

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

Neuron 3720 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0000

Data Index: 493699 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1000878 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1182661 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1735. Min Act: -0.0000

Data Index: 205732 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1668. Min Act: -0.0000

Data Index: 53779 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1656. Min Act: -0.0000

Data Index: 379971 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1136410 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1050383 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1494. Min Act: -0.0000

Data Index: 180607 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1535. Min Act: -0.0000

Data Index: 115399 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1482. Min Act: -0.0000

Data Index: 512756 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1397. Min Act: -0.0000

Data Index: 580474 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1096151 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1104068 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1436. Min Act: -0.0000

Data Index: 208640 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1356. Min Act: 0.0000

Data Index: 1339140 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1426. Min Act: -0.0000

Data Index: 785036 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1421. Min Act: -0.0000

Data Index: 263707 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1215235 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1308. Min Act: -0.0000

Data Index: 680461 (C4 (Web Text))

Max Activating Token Index: 209