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

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

Neuron 1079 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: 2.5618. Min Range: -2.5618

Max Act: 2.5618. Min Act: -0.0000

Data Index: 306236 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.3420. Min Act: -0.0000

Data Index: 541002 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.1489. Min Act: -0.0000

Data Index: 173707 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.3574. Min Act: -0.0000

Data Index: 780186 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.3169. Min Act: -0.0000

Data Index: 795666 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1224077 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.2588. Min Act: -0.0000

Data Index: 578493 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.1031. Min Act: -0.0000

Data Index: 1122954 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.0721. Min Act: -0.0000

Data Index: 316674 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.0430. Min Act: -0.0000

Data Index: 1103685 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9683. Min Act: -0.0000

Data Index: 934731 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9459. Min Act: -0.0000

Data Index: 328449 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.0835. Min Act: -0.0000

Data Index: 24152 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.1447. Min Act: -0.0000

Data Index: 51403 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 2.5618. Min Range: -2.5618

Max Act: 2.0246. Min Act: -0.0000

Data Index: 366430 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9618. Min Act: -0.0000

Data Index: 100409 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9573. Min Act: -0.0000

Data Index: 758209 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9429. Min Act: -0.0000

Data Index: 1124037 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1248295 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 2.5618. Min Range: -2.5618

Max Act: 1.9134. Min Act: -0.0000

Data Index: 75694 (C4 (Web Text))

Max Activating Token Index: 748