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

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

Neuron 677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1438877 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7645. Min Act: -0.0001

Data Index: 1422934 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1477928 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1607978 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6518. Min Act: -0.0001

Data Index: 1536824 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7028. Min Act: -0.0001

Data Index: 1380345 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5969. Min Act: -0.0001

Data Index: 1421310 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1387370 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6474. Min Act: -0.0001

Data Index: 1594744 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1382634 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7181. Min Act: -0.0001

Data Index: 1631163 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6061. Min Act: -0.0001

Data Index: 1628251 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1539975 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1527203 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6040. Min Act: -0.0001

Data Index: 1567645 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6457. Min Act: -0.0001

Data Index: 1525264 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6066. Min Act: -0.0001

Data Index: 1577345 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6473. Min Act: -0.0001

Data Index: 1500842 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1572500 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6249. Min Act: -0.0001

Data Index: 1488086 (Python Code)

Max Activating Token Index: 514