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

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

Neuron 3799 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.0000

Data Index: 504093 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1015567 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8499. Min Act: -0.0000

Data Index: 643461 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8158. Min Act: -0.0001

Data Index: 476753 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9582. Min Act: -0.0001

Data Index: 111400 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1278694 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1248221 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1286197 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.6274. Min Act: -0.0000

Data Index: 958324 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1087367 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.6143. Min Act: -0.0000

Data Index: 764045 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.6011. Min Act: -0.0000

Data Index: 590138 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5591. Min Act: -0.0001

Data Index: 277503 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.4741. Min Act: -0.0001

Data Index: 8043 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5851. Min Act: -0.0001

Data Index: 1153143 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5657. Min Act: -0.0000

Data Index: 669728 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.4682. Min Act: -0.0000

Data Index: 101 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5635. Min Act: -0.0001

Data Index: 785477 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5567. Min Act: -0.0001

Data Index: 756930 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.5184. Min Act: -0.0000

Data Index: 409787 (C4 (Web Text))

Max Activating Token Index: 308