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

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

Neuron 3811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0769. Min Range: -2.0769

Max Act: 2.0769. Min Act: -0.0000

Data Index: 826676 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1254034 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.6965. Min Act: -0.0000

Data Index: 445589 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.8624. Min Act: -0.0000

Data Index: 445223 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.7415. Min Act: -0.0000

Data Index: 179674 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.7429. Min Act: -0.0000

Data Index: 931973 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.3711. Min Act: -0.0000

Data Index: 902032 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.4199. Min Act: -0.0000

Data Index: 186198 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.3784. Min Act: -0.0000

Data Index: 909499 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.6018. Min Act: -0.0000

Data Index: 879157 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.2514. Min Act: -0.0000

Data Index: 539560 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1223890 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.1509. Min Act: -0.0000

Data Index: 968302 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1020137 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.2211. Min Act: -0.0000

Data Index: 680157 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1340095 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.3223. Min Act: -0.0000

Data Index: 891546 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.1602. Min Act: -0.0000

Data Index: 189537 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.1192. Min Act: -0.0000

Data Index: 892065 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 2.0769. Min Range: -2.0769

Max Act: 1.2496. Min Act: -0.0000

Data Index: 560420 (C4 (Web Text))

Max Activating Token Index: 27