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

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

Neuron 1042 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1468. Min Range: -4.1468

Max Act: 4.1468. Min Act: -0.0000

Data Index: 498794 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.7189. Min Act: -0.0000

Data Index: 833638 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.7067. Min Act: -0.0000

Data Index: 1528640 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6954. Min Act: -0.0000

Data Index: 1222697 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6900. Min Act: -0.0000

Data Index: 271168 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6713. Min Act: -0.0000

Data Index: 667485 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.8174. Min Act: -0.0000

Data Index: 958155 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6160. Min Act: -0.0000

Data Index: 1108012 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6046. Min Act: -0.0000

Data Index: 403916 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.6383. Min Act: -0.0000

Data Index: 1434822 (Python Code)

Max Activating Token Index: 916

Text #10

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.7461. Min Act: -0.0000

Data Index: 105150 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.4316. Min Act: -0.0000

Data Index: 171197 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5967. Min Act: -0.0000

Data Index: 1608101 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5794. Min Act: -0.0000

Data Index: 687083 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5480. Min Act: -0.0000

Data Index: 1620038 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5627. Min Act: -0.0000

Data Index: 22000 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5316. Min Act: -0.0000

Data Index: 653486 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.4973. Min Act: -0.0000

Data Index: 462943 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.5095. Min Act: -0.0000

Data Index: 63217 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 4.1468. Min Range: -4.1468

Max Act: 3.4885. Min Act: -0.0000

Data Index: 844754 (C4 (Web Text))

Max Activating Token Index: 554