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

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

Neuron 5222 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: 2.5090. Min Range: -2.5090

Max Act: 2.5090. Min Act: -0.0000

Data Index: 908686 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 2.5090. Min Range: -2.5090

Max Act: 2.4856. Min Act: -0.0000

Data Index: 891228 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 2.5090. Min Range: -2.5090

Max Act: 2.1993. Min Act: -0.0000

Data Index: 1124222 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.5090. Min Range: -2.5090

Max Act: 2.0897. Min Act: -0.0000

Data Index: 1605136 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 2.5090. Min Range: -2.5090

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1276983 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1510005 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.9309. Min Act: -0.0000

Data Index: 1617538 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8943. Min Act: -0.0000

Data Index: 496016 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1490528 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.9126. Min Act: -0.0000

Data Index: 1279266 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1384523 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1527231 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1470408 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1431313 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8234. Min Act: -0.0000

Data Index: 1377202 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8299. Min Act: -0.0000

Data Index: 694594 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.9061. Min Act: -0.0000

Data Index: 1546156 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1513958 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1409162 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 2.5090. Min Range: -2.5090

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1454489 (Python Code)

Max Activating Token Index: 721