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

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

Neuron 1748 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2499. Min Range: -2.2499

Max Act: 2.2499. Min Act: -0.0000

Data Index: 809223 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 2.2499. Min Range: -2.2499

Max Act: 2.0575. Min Act: -0.0000

Data Index: 159338 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.8793. Min Act: -0.0000

Data Index: 139836 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.8898. Min Act: -0.0000

Data Index: 58061 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.7103. Min Act: -0.0000

Data Index: 8193 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1139079 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6725. Min Act: -0.0000

Data Index: 1311174 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6497. Min Act: -0.0000

Data Index: 449566 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6355. Min Act: -0.0000

Data Index: 977574 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1043836 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6299. Min Act: -0.0000

Data Index: 557820 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6092. Min Act: -0.0000

Data Index: 886916 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5826. Min Act: -0.0000

Data Index: 84089 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5746. Min Act: -0.0000

Data Index: 873039 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.6695. Min Act: -0.0000

Data Index: 748192 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1062649 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5616. Min Act: -0.0000

Data Index: 839677 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5419. Min Act: -0.0000

Data Index: 1347853 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1604222 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 2.2499. Min Range: -2.2499

Max Act: 1.5238. Min Act: -0.0000

Data Index: 951103 (C4 (Web Text))

Max Activating Token Index: 283