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

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

Neuron 2805 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.4222. Min Act: -0.0000

Data Index: 516081 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3919. Min Act: -0.0000

Data Index: 668672 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1631290 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1487579 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1644844 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3477. Min Act: -0.0000

Data Index: 88440 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1584492 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1448759 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1042225 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2912. Min Act: -0.0000

Data Index: 240030 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3002. Min Act: -0.0000

Data Index: 225529 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2832. Min Act: 0.0000

Data Index: 1621573 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1467359 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1648468 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2715. Min Act: -0.0000

Data Index: 687044 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2593. Min Act: -0.0000

Data Index: 223645 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1042652 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1370195 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2811. Min Act: -0.0000

Data Index: 11124 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1478065 (Python Code)

Max Activating Token Index: 463