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

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

Neuron 4094 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1527886 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1300457 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1298702 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1211678 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1181443 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1588244 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0871. Min Act: -0.0000

Data Index: 199759 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0863. Min Act: -0.0000

Data Index: 735258 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0826. Min Act: -0.0001

Data Index: 489173 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0833. Min Act: -0.0000

Data Index: 824884 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1362971 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0828. Min Act: -0.0000

Data Index: 984718 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1411373 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0794. Min Act: -0.0000

Data Index: 759234 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0757. Min Act: -0.0000

Data Index: 312897 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0748. Min Act: -0.0000

Data Index: 388972 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1242323 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1476097 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0762. Min Act: -0.0000

Data Index: 58606 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0737. Min Act: -0.0000

Data Index: 606329 (C4 (Web Text))

Max Activating Token Index: 242