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

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

Neuron 4582 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2484. Min Act: -0.0000

Data Index: 193947 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2557. Min Act: -0.0000

Data Index: 383797 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2526. Min Act: -0.0000

Data Index: 96851 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2577. Min Act: -0.0000

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2375. Min Act: -0.0000

Data Index: 278036 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1056894 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2187. Min Act: -0.0000

Data Index: 158343 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2260. Min Act: -0.0000

Data Index: 571087 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1129511 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2385. Min Act: -0.0000

Data Index: 293479 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2038. Min Act: -0.0000

Data Index: 339103 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1698. Min Act: -0.0000

Data Index: 79497 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1497. Min Act: -0.0000

Data Index: 363765 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1600. Min Act: -0.0000

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1588. Min Act: -0.0000

Data Index: 890674 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1465. Min Act: -0.0000

Data Index: 760572 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1339. Min Act: -0.0000

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1366. Min Act: -0.0000

Data Index: 552476 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1295. Min Act: -0.0000

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 495