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

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

Neuron 291 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1711. Min Range: -2.1711

Max Act: 2.1711. Min Act: -0.0000

Data Index: 430897 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.8002. Min Act: -0.0001

Data Index: 447137 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7175. Min Act: -0.0001

Data Index: 423814 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1142852 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.8607. Min Act: -0.0000

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.8845. Min Act: -0.0000

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7593. Min Act: -0.0000

Data Index: 483576 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7738. Min Act: -0.0001

Data Index: 82637 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1059390 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7498. Min Act: -0.0000

Data Index: 707673 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6753. Min Act: -0.0001

Data Index: 410283 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6428. Min Act: -0.0000

Data Index: 264188 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7195. Min Act: -0.0001

Data Index: 624713 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6144. Min Act: -0.0001

Data Index: 848851 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.4690. Min Act: -0.0001

Data Index: 800871 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6718. Min Act: -0.0000

Data Index: 225904 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6203. Min Act: -0.0001

Data Index: 1529893 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.7042. Min Act: -0.0000

Data Index: 997623 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.4245. Min Act: -0.0001

Data Index: 1052875 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 2.1711. Min Range: -2.1711

Max Act: 1.6014. Min Act: -0.0001

Data Index: 407584 (C4 (Web Text))

Max Activating Token Index: 38