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

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

Neuron 5617 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: 1.1359. Min Range: -1.1359

Max Act: 1.1359. Min Act: -0.0000

Data Index: 599631 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1158736 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1149216 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0144. Min Act: -0.0000

Data Index: 245256 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.1358. Min Act: -0.0000

Data Index: 296871 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9817. Min Act: -0.0000

Data Index: 927851 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.1070. Min Act: -0.0000

Data Index: 454395 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0247. Min Act: -0.0000

Data Index: 511839 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1048613 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0510. Min Act: -0.0000

Data Index: 399452 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9352. Min Act: -0.0000

Data Index: 667121 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1246147 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9594. Min Act: -0.0000

Data Index: 442371 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9521. Min Act: -0.0000

Data Index: 379773 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9504. Min Act: -0.0000

Data Index: 2453 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1293270 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9542. Min Act: -0.0000

Data Index: 649694 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9482. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9103. Min Act: -0.0000

Data Index: 206770 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8543. Min Act: -0.0000

Data Index: 150752 (C4 (Web Text))

Max Activating Token Index: 860