Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3631 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.9571. Min Act: -0.0000

Data Index: 450241 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1129631 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1356158 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.7098. Min Act: -0.0000

Data Index: 889591 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.7246. Min Act: -0.0000

Data Index: 604390 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6952. Min Act: -0.0000

Data Index: 756198 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1262909 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1546473 (Python Code)

Max Activating Token Index: 422

Text #8

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1332145 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1287271 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6876. Min Act: -0.0000

Data Index: 888909 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1024182 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6817. Min Act: -0.0000

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6634. Min Act: -0.0000

Data Index: 238002 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6772. Min Act: 0.0001

Data Index: 629414 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6828. Min Act: -0.0000

Data Index: 243708 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6352. Min Act: -0.0000

Data Index: 330909 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6496. Min Act: -0.0000

Data Index: 315639 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6844. Min Act: -0.0000

Data Index: 930354 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.9571. Min Range: -0.9571

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1187926 (C4 (Web Text))

Max Activating Token Index: 411