Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.2205. Min Act: -0.0005

Data Index: 773196 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.2024. Min Act: -0.0005

Data Index: 26759 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1710. Min Act: -0.0005

Data Index: 464707 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1823. Min Act: -0.0005

Data Index: 576770 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1571. Min Act: -0.0005

Data Index: 1098876 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1661. Min Act: -0.0005

Data Index: 244559 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1501. Min Act: -0.0005

Data Index: 865613 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1596. Min Act: -0.0005

Data Index: 1100904 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1415. Min Act: -0.0005

Data Index: 1198393 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1502. Min Act: -0.0005

Data Index: 433894 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1471. Min Act: -0.0005

Data Index: 306773 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1534. Min Act: -0.0005

Data Index: 777996 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1527. Min Act: -0.0005

Data Index: 631796 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1518. Min Act: -0.0005

Data Index: 1273293 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1461. Min Act: -0.0005

Data Index: 1075075 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1516. Min Act: -0.0005

Data Index: 945796 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1438. Min Act: -0.0005

Data Index: 142837 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1498. Min Act: -0.0005

Data Index: 908170 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1426. Min Act: -0.0005

Data Index: 930200 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1466. Min Act: -0.0005

Data Index: 1050613 (C4 (Web Text))

Max Activating Token Index: 694