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

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

Neuron 5450 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: 1.6436. Min Range: -1.6436

Max Act: 1.6436. Min Act: -0.0000

Data Index: 437753 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.5441. Min Act: -0.0000

Data Index: 864532 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.4523. Min Act: -0.0000

Data Index: 248520 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.2561. Min Act: -0.0000

Data Index: 699681 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.1096. Min Act: -0.0000

Data Index: 897999 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1512772 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.9713. Min Act: -0.0000

Data Index: 809729 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.9899. Min Act: -0.0000

Data Index: 122565 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.9989. Min Act: -0.0000

Data Index: 961254 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8815. Min Act: -0.0000

Data Index: 178891 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8764. Min Act: -0.0000

Data Index: 933570 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.6436. Min Range: -1.6436

Max Act: 1.0444. Min Act: -0.0000

Data Index: 269326 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8781. Min Act: -0.0000

Data Index: 610820 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8769. Min Act: -0.0000

Data Index: 611261 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8351. Min Act: -0.0000

Data Index: 668237 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.9161. Min Act: -0.0000

Data Index: 816977 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1187170 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8242. Min Act: -0.0000

Data Index: 189674 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.8529. Min Act: -0.0000

Data Index: 205194 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.6436. Min Range: -1.6436

Max Act: 0.7599. Min Act: -0.0000

Data Index: 826228 (C4 (Web Text))

Max Activating Token Index: 495