Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1910 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0001

Data Index: 318532 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0679. Min Act: -0.0001

Data Index: 855476 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0648. Min Act: -0.0001

Data Index: 298851 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1159929 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0588. Min Act: -0.0001

Data Index: 739852 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0559. Min Act: -0.0001

Data Index: 689487 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0577. Min Act: -0.0001

Data Index: 337117 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0543. Min Act: -0.0001

Data Index: 846464 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1124732 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0613. Min Act: -0.0001

Data Index: 889274 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0556. Min Act: -0.0001

Data Index: 544585 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0555. Min Act: -0.0001

Data Index: 595697 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1288145 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1399148 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0543. Min Act: -0.0001

Data Index: 472139 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0584. Min Act: -0.0001

Data Index: 813031 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0585. Min Act: -0.0001

Data Index: 195087 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1268288 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0558. Min Act: -0.0001

Data Index: 441442 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0533. Min Act: -0.0001

Data Index: 97815 (C4 (Web Text))

Max Activating Token Index: 293