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

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

Neuron 404 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8259. Min Act: -0.0001

Data Index: 570633 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 3.0340. Min Range: -3.0340

Max Act: 3.0340. Min Act: -0.0001

Data Index: 1320661 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7450. Min Act: -0.0001

Data Index: 1335710 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7180. Min Act: -0.0001

Data Index: 376139 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5660. Min Act: -0.0001

Data Index: 103946 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.6019. Min Act: -0.0001

Data Index: 1335456 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.3834. Min Act: -0.0001

Data Index: 27996 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4827. Min Act: -0.0001

Data Index: 258165 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.6082. Min Act: -0.0001

Data Index: 183973 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5848. Min Act: -0.0001

Data Index: 283435 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5977. Min Act: -0.0001

Data Index: 823228 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4292. Min Act: -0.0001

Data Index: 1304442 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4025. Min Act: -0.0001

Data Index: 1234822 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4205. Min Act: -0.0001

Data Index: 1029525 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.2795. Min Act: -0.0001

Data Index: 237232 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.3918. Min Act: -0.0001

Data Index: 1237515 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.3543. Min Act: -0.0001

Data Index: 1319142 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.3475. Min Act: -0.0001

Data Index: 1090360 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4535. Min Act: -0.0001

Data Index: 1157676 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.1928. Min Act: -0.0001

Data Index: 982557 (C4 (Web Text))

Max Activating Token Index: 846