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

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

Neuron 542 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.8162. Min Act: -0.0000

Data Index: 763233 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6444. Min Act: -0.0000

Data Index: 772774 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.5036. Min Act: -0.0000

Data Index: 153440 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.4703. Min Act: -0.0000

Data Index: 234225 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.3523. Min Act: -0.0000

Data Index: 13465 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.2085. Min Act: -0.0000

Data Index: 415472 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.1621. Min Act: -0.0000

Data Index: 322761 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.1667. Min Act: -0.0000

Data Index: 438035 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.1202. Min Act: -0.0000

Data Index: 388148 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.9268. Min Act: -0.0000

Data Index: 468484 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.0478. Min Act: -0.0000

Data Index: 1014599 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.0733. Min Act: -0.0000

Data Index: 1238014 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.0175. Min Act: -0.0000

Data Index: 63134 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.0077. Min Act: -0.0000

Data Index: 765606 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.6969. Min Act: -0.0000

Data Index: 128691 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.9901. Min Act: -0.0000

Data Index: 807155 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.9972. Min Act: -0.0000

Data Index: 515047 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.1320. Min Act: -0.0000

Data Index: 654567 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.9326. Min Act: -0.0000

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 4.8162. Min Range: -4.8162

Max Act: 3.8869. Min Act: -0.0000

Data Index: 400651 (C4 (Web Text))

Max Activating Token Index: 37