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

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

Neuron 890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2765. Min Act: -0.0000

Data Index: 165681 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1009474 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2806. Min Act: -0.0000

Data Index: 624850 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1263874 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2588. Min Act: -0.0000

Data Index: 25069 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2544. Min Act: -0.0000

Data Index: 360567 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2520. Min Act: -0.0000

Data Index: 272870 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1033251 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2615. Min Act: -0.0000

Data Index: 293154 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1129268 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2407. Min Act: -0.0000

Data Index: 505363 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2573. Min Act: -0.0000

Data Index: 253120 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2520. Min Act: -0.0000

Data Index: 930014 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2645. Min Act: -0.0000

Data Index: 150380 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2479. Min Act: -0.0000

Data Index: 917172 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2455. Min Act: -0.0000

Data Index: 369744 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1062660 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2592. Min Act: -0.0000

Data Index: 259478 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2468. Min Act: -0.0000

Data Index: 207191 (C4 (Web Text))

Max Activating Token Index: 675