Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3342. Min Act: -0.0000

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3240. Min Act: -0.0000

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2879. Min Act: -0.0000

Data Index: 912131 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2745. Min Act: -0.0000

Data Index: 176920 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2796. Min Act: -0.0000

Data Index: 813140 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2564. Min Act: -0.0000

Data Index: 496587 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2564. Min Act: -0.0000

Data Index: 127072 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2627. Min Act: -0.0000

Data Index: 985134 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2623. Min Act: -0.0000

Data Index: 433915 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1288426 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1060558 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1031452 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2491. Min Act: -0.0000

Data Index: 702281 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2528. Min Act: -0.0000

Data Index: 912585 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2299. Min Act: -0.0000

Data Index: 472090 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2392. Min Act: -0.0000

Data Index: 321667 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1213724 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1243201 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2442. Min Act: -0.0000

Data Index: 671789 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2364. Min Act: -0.0000

Data Index: 699174 (C4 (Web Text))

Max Activating Token Index: 633