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

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

Neuron 4334 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.2509. Min Act: -0.0000

Data Index: 589482 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1116121 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.1837. Min Act: -0.0000

Data Index: 798834 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1534775 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1289397 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0811. Min Act: -0.0000

Data Index: 985998 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0692. Min Act: -0.0000

Data Index: 677834 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.1232. Min Act: -0.0000

Data Index: 669477 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1167292 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0111. Min Act: -0.0000

Data Index: 324781 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0851. Min Act: -0.0000

Data Index: 394198 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1610274 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1259957 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1183075 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1177067 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9658. Min Act: -0.0000

Data Index: 672339 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0217. Min Act: -0.0000

Data Index: 270898 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.2509. Min Range: -1.2509

Max Act: 1.0008. Min Act: -0.0000

Data Index: 426608 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1402691 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 1.2509. Min Range: -1.2509

Max Act: 0.9834. Min Act: -0.0000

Data Index: 800686 (C4 (Web Text))

Max Activating Token Index: 605