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

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

Neuron 3325 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.2003. Min Act: -0.0001

Data Index: 943738 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.2029. Min Act: -0.0001

Data Index: 735307 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1704. Min Act: -0.0001

Data Index: 300948 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1713. Min Act: -0.0001

Data Index: 838100 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1627. Min Act: -0.0001

Data Index: 963926 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1132137 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1194123 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1583. Min Act: -0.0001

Data Index: 703262 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1423. Min Act: -0.0001

Data Index: 578470 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1434. Min Act: -0.0001

Data Index: 303559 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1548. Min Act: -0.0001

Data Index: 906359 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1459. Min Act: -0.0001

Data Index: 758555 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1044032 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1419. Min Act: -0.0001

Data Index: 363234 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1200886 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1730. Min Act: -0.0001

Data Index: 489435 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1482. Min Act: -0.0001

Data Index: 172992 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1330. Min Act: -0.0001

Data Index: 13275 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1398. Min Act: -0.0001

Data Index: 421393 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.2029. Min Range: -0.2029

Max Act: 0.1473. Min Act: -0.0001

Data Index: 477096 (C4 (Web Text))

Max Activating Token Index: 329