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

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

Neuron 2950 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: 2.1648. Min Range: -2.1648

Max Act: 2.1648. Min Act: -0.0000

Data Index: 1311518 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.7594. Min Act: -0.0000

Data Index: 847015 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.6699. Min Act: -0.0000

Data Index: 465233 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.7371. Min Act: -0.0000

Data Index: 766562 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1043498 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.4545. Min Act: -0.0000

Data Index: 847110 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.4979. Min Act: -0.0000

Data Index: 743397 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.5490. Min Act: -0.0000

Data Index: 468860 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1330544 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1352899 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.2977. Min Act: -0.0000

Data Index: 724683 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1341612 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.3265. Min Act: -0.0000

Data Index: 891702 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.3023. Min Act: -0.0000

Data Index: 571448 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.2105. Min Act: -0.0000

Data Index: 376084 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.1766. Min Act: -0.0000

Data Index: 346807 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1217686 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.1937. Min Act: -0.0000

Data Index: 892546 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.1992. Min Act: -0.0000

Data Index: 498274 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 2.1648. Min Range: -2.1648

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1639756 (Python Code)

Max Activating Token Index: 500