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

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

Neuron 3320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.9231. Min Act: -0.0001

Data Index: 914630 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7847. Min Act: -0.0001

Data Index: 701637 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1015752 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6845. Min Act: -0.0001

Data Index: 458113 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6646. Min Act: -0.0001

Data Index: 543994 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6745. Min Act: -0.0000

Data Index: 669182 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6702. Min Act: -0.0001

Data Index: 115926 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6355. Min Act: -0.0001

Data Index: 1313621 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6578. Min Act: -0.0001

Data Index: 378460 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1232658 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6382. Min Act: -0.0001

Data Index: 897805 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6570. Min Act: -0.0000

Data Index: 376570 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6570. Min Act: -0.0000

Data Index: 359798 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6279. Min Act: -0.0001

Data Index: 261513 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5826. Min Act: -0.0001

Data Index: 223180 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6126. Min Act: -0.0001

Data Index: 852819 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5947. Min Act: -0.0001

Data Index: 834287 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5995. Min Act: -0.0001

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5952. Min Act: -0.0000

Data Index: 474222 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1223056 (C4 (Web Text))

Max Activating Token Index: 237