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

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

Neuron 1342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1249818 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8541. Min Act: -0.0001

Data Index: 1232649 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.9098. Min Act: -0.0001

Data Index: 540869 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1023337 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1049568 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8163. Min Act: -0.0001

Data Index: 400801 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1037507 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8340. Min Act: -0.0001

Data Index: 964674 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1180990 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1159871 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7345. Min Act: -0.0000

Data Index: 302742 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1040629 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1183431 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7691. Min Act: -0.0001

Data Index: 803818 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7720. Min Act: -0.0000

Data Index: 904628 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7453. Min Act: -0.0001

Data Index: 1169655 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7423. Min Act: -0.0001

Data Index: 613783 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1297749 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7618. Min Act: -0.0001

Data Index: 530566 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7721. Min Act: -0.0001

Data Index: 387158 (C4 (Web Text))

Max Activating Token Index: 212