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

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

Neuron 5647 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.5842. Min Act: -0.0000

Data Index: 182013 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.6339. Min Act: -0.0000

Data Index: 490244 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1758. Min Act: -0.0001

Data Index: 41540 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.0709. Min Act: -0.0001

Data Index: 150204 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1740. Min Act: -0.0000

Data Index: 279277 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4010. Min Act: -0.0001

Data Index: 1002612 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3366. Min Act: -0.0001

Data Index: 1353030 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.6140. Min Act: -0.0001

Data Index: 210819 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3225. Min Act: -0.0001

Data Index: 1063664 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4500. Min Act: -0.0000

Data Index: 14052 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.2392. Min Act: -0.0001

Data Index: 127599 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.3694. Min Act: -0.0001

Data Index: 649587 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1589. Min Act: -0.0000

Data Index: 364706 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1660. Min Act: -0.0000

Data Index: 89692 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4025. Min Act: -0.0000

Data Index: 231489 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1030250 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1622. Min Act: -0.0001

Data Index: 590926 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.1631. Min Act: -0.0001

Data Index: 759025 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 2.6339. Min Range: -2.6339

Max Act: 2.4002. Min Act: -0.0001

Data Index: 740679 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 2.6339. Min Range: -2.6339

Max Act: 1.9960. Min Act: -0.0001

Data Index: 1104461 (C4 (Web Text))

Max Activating Token Index: 884