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

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

Neuron 204 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.4618. Min Act: 0.0001

Data Index: 1546609 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.4563. Min Act: 0.0001

Data Index: 1425934 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1422. Min Act: 0.0000

Data Index: 916491 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1668. Min Act: 0.0001

Data Index: 1481180 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1302143 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0002. Min Act: 0.0002

Data Index: 1524304 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9248. Min Act: 0.0000

Data Index: 83 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8369. Min Act: -0.0000

Data Index: 679695 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9081. Min Act: 0.0000

Data Index: 1279874 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8313. Min Act: 0.0002

Data Index: 1491180 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8113. Min Act: -0.0000

Data Index: 305686 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8175. Min Act: -0.0000

Data Index: 652776 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8343. Min Act: -0.0000

Data Index: 668200 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7736. Min Act: 0.0001

Data Index: 413495 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8227. Min Act: 0.0001

Data Index: 1435388 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1339715 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7857. Min Act: -0.0000

Data Index: 401452 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7785. Min Act: -0.0000

Data Index: 393176 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7281. Min Act: -0.0000

Data Index: 882329 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.7665. Min Act: 0.0000

Data Index: 1462515 (Python Code)

Max Activating Token Index: 708