Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 63 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2568. Min Act: -0.0001

Data Index: 475291 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2621. Min Act: -0.0001

Data Index: 753081 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2213. Min Act: -0.0001

Data Index: 464065 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2524. Min Act: -0.0001

Data Index: 412986 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1975 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2345. Min Act: -0.0001

Data Index: 641429 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2529. Min Act: -0.0001

Data Index: 868624 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2288. Min Act: -0.0001

Data Index: 79478 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2356. Min Act: -0.0001

Data Index: 96757 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1132954 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2196. Min Act: -0.0001

Data Index: 191734 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2395. Min Act: -0.0001

Data Index: 583647 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2068. Min Act: -0.0001

Data Index: 516201 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1226031 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2112. Min Act: -0.0001

Data Index: 83923 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2011. Min Act: -0.0001

Data Index: 942280 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1121594 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2181. Min Act: -0.0001

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1978. Min Act: -0.0001

Data Index: 66517 (C4 (Web Text))

Max Activating Token Index: 833