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

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

Neuron 1975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1382366 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.3280. Min Act: -0.0000

Data Index: 1571947 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1601. Min Act: -0.0000

Data Index: 1400928 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 2.3280. Min Range: -2.3280

Max Act: 1.9785. Min Act: -0.0000

Data Index: 1465562 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.2060. Min Act: -0.0000

Data Index: 1640400 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.2816. Min Act: -0.0000

Data Index: 1591300 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1078. Min Act: -0.0000

Data Index: 1642712 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1617. Min Act: -0.0000

Data Index: 1388153 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1412. Min Act: -0.0000

Data Index: 1552016 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1591946 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1495505 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0626. Min Act: -0.0000

Data Index: 1488376 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0599. Min Act: -0.0000

Data Index: 1404020 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0486. Min Act: -0.0000

Data Index: 1377988 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0556. Min Act: -0.0000

Data Index: 1360149 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0959. Min Act: -0.0000

Data Index: 1654530 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1119. Min Act: -0.0000

Data Index: 1600463 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1479. Min Act: -0.0000

Data Index: 1635840 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1629751 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 2.3280. Min Range: -2.3280

Max Act: 2.0882. Min Act: -0.0000

Data Index: 1636484 (Python Code)

Max Activating Token Index: 286