Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4975 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.5270. Min Act: -0.0000

Data Index: 317913 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.5110. Min Act: -0.0000

Data Index: 9434 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.5977. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.3145. Min Act: -0.0000

Data Index: 1180876 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.2213. Min Act: -0.0000

Data Index: 1290056 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.0317. Min Act: -0.0000

Data Index: 897345 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.1336. Min Act: -0.0000

Data Index: 709219 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9458. Min Act: -0.0000

Data Index: 1039329 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 3.5977. Min Range: -3.5977

Max Act: 3.0679. Min Act: -0.0000

Data Index: 1242185 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9909. Min Act: -0.0000

Data Index: 500762 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9755. Min Act: -0.0000

Data Index: 627802 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8229. Min Act: -0.0000

Data Index: 340568 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8083. Min Act: -0.0000

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.6260. Min Act: -0.0000

Data Index: 1284156 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8698. Min Act: -0.0000

Data Index: 354461 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8635. Min Act: -0.0000

Data Index: 42097 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9861. Min Act: -0.0000

Data Index: 389457 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.8363. Min Act: -0.0000

Data Index: 555439 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.9370. Min Act: -0.0000

Data Index: 733754 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 3.5977. Min Range: -3.5977

Max Act: 2.7647. Min Act: -0.0000

Data Index: 618281 (C4 (Web Text))

Max Activating Token Index: 639