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

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

Neuron 3054 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: 1.6534. Min Range: -1.6534

Max Act: 1.6534. Min Act: -0.0000

Data Index: 1451331 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.4124. Min Act: -0.0001

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.5651. Min Act: -0.0001

Data Index: 657520 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.4732. Min Act: -0.0001

Data Index: 439332 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.4402. Min Act: -0.0001

Data Index: 812726 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.5951. Min Act: -0.0001

Data Index: 725198 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.3954. Min Act: -0.0001

Data Index: 1301163 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.4317. Min Act: -0.0001

Data Index: 952241 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.5515. Min Act: -0.0001

Data Index: 461282 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.4082. Min Act: -0.0001

Data Index: 1491979 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2497. Min Act: -0.0001

Data Index: 1064439 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.3904. Min Act: -0.0001

Data Index: 659678 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2672. Min Act: -0.0001

Data Index: 1136696 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.3327. Min Act: -0.0001

Data Index: 825086 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2852. Min Act: -0.0001

Data Index: 429227 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.1929. Min Act: -0.0001

Data Index: 864573 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2206. Min Act: -0.0001

Data Index: 967603 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2415. Min Act: -0.0001

Data Index: 493450 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2646. Min Act: -0.0001

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.6534. Min Range: -1.6534

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1447820 (Python Code)

Max Activating Token Index: 373