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

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

Neuron 1573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2811. Min Act: -0.0001

Data Index: 718728 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2853. Min Act: -0.0001

Data Index: 871915 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2989. Min Act: -0.0001

Data Index: 382769 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2917. Min Act: -0.0001

Data Index: 118024 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.3034. Min Act: -0.0001

Data Index: 21043 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2620. Min Act: -0.0001

Data Index: 954925 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2643. Min Act: -0.0001

Data Index: 227490 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2802. Min Act: -0.0001

Data Index: 1158838 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2807. Min Act: -0.0001

Data Index: 901329 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1102634 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2739. Min Act: -0.0001

Data Index: 119552 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1100573 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2479. Min Act: -0.0001

Data Index: 406627 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2503. Min Act: -0.0001

Data Index: 490372 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1080982 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1266900 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2362. Min Act: -0.0001

Data Index: 38035 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2475. Min Act: -0.0001

Data Index: 705940 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1008379 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2408. Min Act: -0.0001

Data Index: 868261 (C4 (Web Text))

Max Activating Token Index: 3