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

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

Neuron 4989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.5412. Min Act: -0.0000

Data Index: 51483 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.3202. Min Act: -0.0000

Data Index: 48281 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.3197. Min Act: -0.0000

Data Index: 957876 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1156030 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.2581. Min Act: -0.0000

Data Index: 583541 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.2603. Min Act: -0.0000

Data Index: 521285 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.2656. Min Act: -0.0000

Data Index: 163069 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.1915. Min Act: -0.0000

Data Index: 145651 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.2508. Min Act: -0.0000

Data Index: 234953 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1055189 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1033094 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.1006. Min Act: -0.0000

Data Index: 238577 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1295949 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.1520. Min Act: -0.0000

Data Index: 557532 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.5412. Min Range: -1.5412

Max Act: 0.9796. Min Act: -0.0000

Data Index: 760697 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.0800. Min Act: -0.0000

Data Index: 310202 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.1169. Min Act: -0.0000

Data Index: 498753 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.1082. Min Act: -0.0001

Data Index: 845696 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.5412. Min Range: -1.5412

Max Act: 1.0238. Min Act: -0.0000

Data Index: 769734 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.5412. Min Range: -1.5412

Max Act: 0.9874. Min Act: -0.0000

Data Index: 309393 (C4 (Web Text))

Max Activating Token Index: 944