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

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

Neuron 3118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5947. Min Act: -0.0001

Data Index: 58363 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.6168. Min Act: -0.0001

Data Index: 603894 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5304. Min Act: -0.0001

Data Index: 594434 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5067. Min Act: -0.0001

Data Index: 152210 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5722. Min Act: -0.0001

Data Index: 55619 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5935. Min Act: -0.0001

Data Index: 796601 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1032630 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4788. Min Act: -0.0001

Data Index: 633689 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5377. Min Act: -0.0001

Data Index: 847444 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5188. Min Act: -0.0001

Data Index: 764659 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5162. Min Act: -0.0001

Data Index: 54490 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5149. Min Act: -0.0001

Data Index: 634934 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1144513 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4937. Min Act: -0.0001

Data Index: 322808 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1217885 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5387. Min Act: -0.0001

Data Index: 877312 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5013. Min Act: -0.0001

Data Index: 248594 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4603. Min Act: -0.0001

Data Index: 282546 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.4980. Min Act: -0.0001

Data Index: 150317 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.6168. Min Range: -0.6168

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1084980 (C4 (Web Text))

Max Activating Token Index: 1015