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

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

Neuron 2224 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: 0.9695. Min Range: -0.9695

Max Act: 0.9695. Min Act: -0.0001

Data Index: 582101 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8917. Min Act: -0.0001

Data Index: 5988 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8990. Min Act: -0.0001

Data Index: 31994 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8913. Min Act: -0.0001

Data Index: 864122 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8857. Min Act: -0.0001

Data Index: 332106 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.9369. Min Act: -0.0001

Data Index: 870759 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8272. Min Act: -0.0001

Data Index: 555341 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8478. Min Act: -0.0001

Data Index: 1054977 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8452. Min Act: -0.0001

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8528. Min Act: -0.0001

Data Index: 556269 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8573. Min Act: -0.0001

Data Index: 103570 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8303. Min Act: -0.0001

Data Index: 1214080 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1142904 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7655. Min Act: -0.0001

Data Index: 1015260 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7845. Min Act: -0.0001

Data Index: 39453 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7733. Min Act: -0.0001

Data Index: 695093 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7977. Min Act: -0.0001

Data Index: 879294 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8092. Min Act: -0.0001

Data Index: 777964 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.6979. Min Act: -0.0001

Data Index: 497752 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7647. Min Act: -0.0001

Data Index: 843170 (C4 (Web Text))

Max Activating Token Index: 771