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

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

Neuron 4258 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: 1.1706. Min Range: -1.1706

Max Act: 1.1706. Min Act: -0.0000

Data Index: 132740 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1413. Min Act: 0.0000

Data Index: 641781 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1278. Min Act: -0.0000

Data Index: 323924 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0517. Min Act: -0.0000

Data Index: 611128 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9756. Min Act: -0.0000

Data Index: 752251 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0061. Min Act: 0.0000

Data Index: 320335 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9256. Min Act: -0.0000

Data Index: 245514 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8988. Min Act: -0.0000

Data Index: 780315 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1074086 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8796. Min Act: -0.0000

Data Index: 856598 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8783. Min Act: -0.0000

Data Index: 329915 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1321397 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8747. Min Act: 0.0000

Data Index: 815837 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8697. Min Act: -0.0000

Data Index: 730038 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8496. Min Act: -0.0000

Data Index: 871426 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1075408 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8372. Min Act: -0.0000

Data Index: 555725 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8283. Min Act: 0.0000

Data Index: 198837 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1242224 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8226. Min Act: -0.0000

Data Index: 610419 (C4 (Web Text))

Max Activating Token Index: 63