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

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

Neuron 1545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3726. Min Act: -0.0000

Data Index: 127384 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3316. Min Act: -0.0000

Data Index: 500444 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1025759 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3170. Min Act: -0.0001

Data Index: 211349 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3006. Min Act: -0.0001

Data Index: 429125 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2905. Min Act: -0.0001

Data Index: 235193 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2814. Min Act: -0.0000

Data Index: 592331 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2461. Min Act: -0.0000

Data Index: 325615 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2533. Min Act: -0.0001

Data Index: 473895 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2670. Min Act: -0.0000

Data Index: 65335 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2563. Min Act: -0.0000

Data Index: 593845 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2702. Min Act: -0.0001

Data Index: 704032 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2617. Min Act: -0.0000

Data Index: 972203 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1037562 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2543. Min Act: -0.0001

Data Index: 908251 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1021071 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2542. Min Act: -0.0000

Data Index: 919075 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2364. Min Act: -0.0001

Data Index: 913020 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1192546 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2601. Min Act: -0.0001

Data Index: 648770 (C4 (Web Text))

Max Activating Token Index: 559