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

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

Neuron 371 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6147. Min Act: -0.0002

Data Index: 1224960 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7308. Min Act: -0.0001

Data Index: 584705 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7151. Min Act: -0.0001

Data Index: 122305 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6019. Min Act: -0.0001

Data Index: 501095 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6111. Min Act: -0.0001

Data Index: 967223 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6429. Min Act: -0.0001

Data Index: 346110 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6781. Min Act: -0.0001

Data Index: 69142 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6363. Min Act: -0.0001

Data Index: 146702 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5633. Min Act: -0.0001

Data Index: 3189 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1045072 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5838. Min Act: -0.0001

Data Index: 50220 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6643. Min Act: -0.0001

Data Index: 657283 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1018265 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5838. Min Act: -0.0001

Data Index: 259464 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5322. Min Act: -0.0002

Data Index: 1149596 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1056524 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6706. Min Act: -0.0001

Data Index: 474311 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5928. Min Act: -0.0001

Data Index: 618812 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5907. Min Act: -0.0002

Data Index: 1000842 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6398. Min Act: -0.0001

Data Index: 849415 (C4 (Web Text))

Max Activating Token Index: 22