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

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

Neuron 2036 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: 0.8417. Min Range: -0.8417

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1474968 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7279. Min Act: -0.0000

Data Index: 635461 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1566906 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1561842 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1593263 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6361. Min Act: -0.0000

Data Index: 822354 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1612840 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1635366 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1165624 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1509427 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1591908 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5549. Min Act: -0.0000

Data Index: 287548 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1390277 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5547. Min Act: -0.0000

Data Index: 583416 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1589220 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5309. Min Act: -0.0000

Data Index: 809917 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1462999 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1591226 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1563481 (Python Code)

Max Activating Token Index: 343

Text #19

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1329828 (C4 (Web Text))

Max Activating Token Index: 663