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

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

Neuron 1436 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3605. Min Range: -2.3605

Max Act: 2.3605. Min Act: -0.0000

Data Index: 177092 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 2.3605. Min Range: -2.3605

Max Act: 2.2260. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.3605. Min Range: -2.3605

Max Act: 2.1695. Min Act: -0.0000

Data Index: 1114859 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 2.3605. Min Range: -2.3605

Max Act: 2.0377. Min Act: -0.0000

Data Index: 101526 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.9295. Min Act: -0.0000

Data Index: 84007 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.7135. Min Act: -0.0000

Data Index: 306578 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.7929. Min Act: -0.0000

Data Index: 176842 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.7756. Min Act: -0.0000

Data Index: 806063 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1305673 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1148081 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.7248. Min Act: -0.0000

Data Index: 896572 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5947. Min Act: -0.0000

Data Index: 865193 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1109292 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5985. Min Act: -0.0000

Data Index: 870897 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5937. Min Act: -0.0000

Data Index: 657151 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5022. Min Act: -0.0000

Data Index: 100443 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1629850 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5648. Min Act: -0.0000

Data Index: 165654 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1277499 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.3605. Min Range: -2.3605

Max Act: 1.5461. Min Act: -0.0000

Data Index: 879991 (C4 (Web Text))

Max Activating Token Index: 680