Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 65 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 254332 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2797. Min Act: -0.0000

Data Index: 487179 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2790. Min Act: -0.0001

Data Index: 374904 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2713. Min Act: -0.0000

Data Index: 734832 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2702. Min Act: -0.0000

Data Index: 545953 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1044376 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2645. Min Act: -0.0001

Data Index: 309756 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2659. Min Act: -0.0000

Data Index: 501753 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2727. Min Act: -0.0000

Data Index: 335303 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2470. Min Act: -0.0000

Data Index: 132939 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2530. Min Act: -0.0000

Data Index: 643556 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2503. Min Act: -0.0000

Data Index: 656470 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2558. Min Act: -0.0000

Data Index: 123965 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2438. Min Act: -0.0000

Data Index: 576909 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2355. Min Act: -0.0000

Data Index: 898737 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1289591 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2417. Min Act: -0.0000

Data Index: 14358 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2255. Min Act: -0.0001

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2401. Min Act: -0.0000

Data Index: 867706 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2373. Min Act: -0.0000

Data Index: 794822 (C4 (Web Text))

Max Activating Token Index: 253