Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.2077. Min Act: -0.0000

Data Index: 16475 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1861. Min Act: -0.0000

Data Index: 168270 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1083537 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1701. Min Act: -0.0000

Data Index: 456869 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1604466 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1602345 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1447327 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1647. Min Act: -0.0000

Data Index: 604579 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1507. Min Act: -0.0000

Data Index: 966998 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1445. Min Act: -0.0000

Data Index: 300647 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1010394 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1492119 (Python Code)

Max Activating Token Index: 583

Text #12

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1340. Min Act: -0.0000

Data Index: 943151 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1458836 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1071451 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1335. Min Act: -0.0000

Data Index: 736275 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1232. Min Act: -0.0000

Data Index: 863751 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1323622 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1270. Min Act: -0.0000

Data Index: 877322 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1221. Min Act: -0.0000

Data Index: 389947 (C4 (Web Text))

Max Activating Token Index: 501