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

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

Neuron 2731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1397. Min Act: -0.0000

Data Index: 124128 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1027. Min Act: -0.0000

Data Index: 460534 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.0714. Min Act: -0.0000

Data Index: 763478 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.0436. Min Act: -0.0000

Data Index: 722773 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.0770. Min Act: -0.0000

Data Index: 938417 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9564. Min Act: -0.0000

Data Index: 263258 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1183107 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8925. Min Act: -0.0000

Data Index: 768492 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8842. Min Act: -0.0000

Data Index: 958150 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8962. Min Act: -0.0000

Data Index: 456662 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1079133 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8556. Min Act: -0.0000

Data Index: 811884 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8745. Min Act: -0.0000

Data Index: 965981 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8855. Min Act: -0.0000

Data Index: 31133 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8309. Min Act: -0.0000

Data Index: 922127 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8518. Min Act: -0.0000

Data Index: 111933 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8556. Min Act: -0.0000

Data Index: 940018 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1283085 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8353. Min Act: -0.0000

Data Index: 111082 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8338. Min Act: -0.0000

Data Index: 901803 (C4 (Web Text))

Max Activating Token Index: 907