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

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

Neuron 3330 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7749. Min Act: -0.0001

Data Index: 150591 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.2157. Min Act: -0.0001

Data Index: 240380 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.2398. Min Act: -0.0001

Data Index: 505448 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.1777. Min Act: -0.0001

Data Index: 87269 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0492. Min Act: -0.0001

Data Index: 452152 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0837. Min Act: -0.0001

Data Index: 736799 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0814. Min Act: -0.0001

Data Index: 991134 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.1349. Min Act: -0.0001

Data Index: 2352 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.1255. Min Act: -0.0001

Data Index: 47353 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0731. Min Act: -0.0001

Data Index: 105697 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0586. Min Act: -0.0001

Data Index: 1233370 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.0556. Min Act: -0.0001

Data Index: 366348 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9702. Min Act: -0.0001

Data Index: 1311537 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9499. Min Act: -0.0001

Data Index: 550775 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1069443 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9453. Min Act: -0.0001

Data Index: 938479 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1179898 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9613. Min Act: -0.0001

Data Index: 336564 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.8068. Min Act: -0.0001

Data Index: 720410 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.7749. Min Range: -1.7749

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1040772 (C4 (Web Text))

Max Activating Token Index: 778