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

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

Neuron 5427 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: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0000

Data Index: 760444 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0910. Min Act: -0.0000

Data Index: 193666 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1045776 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1341853 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0805. Min Act: -0.0000

Data Index: 22053 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0713. Min Act: -0.0000

Data Index: 917831 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0772. Min Act: -0.0000

Data Index: 402971 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0646. Min Act: -0.0000

Data Index: 454035 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0723. Min Act: -0.0000

Data Index: 16236 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0698. Min Act: -0.0000

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0726. Min Act: -0.0000

Data Index: 449704 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0730. Min Act: -0.0000

Data Index: 756669 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0722. Min Act: -0.0000

Data Index: 812674 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0717. Min Act: -0.0001

Data Index: 539253 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0717. Min Act: -0.0000

Data Index: 977812 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1356559 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1060061 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0688. Min Act: -0.0000

Data Index: 226272 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1247956 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0763. Min Act: -0.0000

Data Index: 199942 (C4 (Web Text))

Max Activating Token Index: 897