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

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

Neuron 1305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1500. Min Range: -2.1500

Max Act: 2.1500. Min Act: -0.0000

Data Index: 1544406 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 2.1500. Min Range: -2.1500

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1463686 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 2.1500. Min Range: -2.1500

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1511783 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 2.1500. Min Range: -2.1500

Max Act: 2.0523. Min Act: -0.0000

Data Index: 1446543 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 2.1500. Min Range: -2.1500

Max Act: 2.0102. Min Act: -0.0000

Data Index: 1422167 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1378993 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.9600. Min Act: -0.0000

Data Index: 1573898 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1393882 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1419995 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1581662 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1403503 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1370930 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1465024 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1611439 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1616778 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.6996. Min Act: -0.0000

Data Index: 1401482 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1456248 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1640903 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7271. Min Act: -0.0000

Data Index: 1636799 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 2.1500. Min Range: -2.1500

Max Act: 1.7198. Min Act: -0.0000

Data Index: 1603889 (Python Code)

Max Activating Token Index: 645