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

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

Neuron 3446 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1035. Min Range: -1.1035

Max Act: 1.1035. Min Act: -0.0001

Data Index: 425684 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.8312. Min Act: -0.0001

Data Index: 536873 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1345509 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.7110. Min Act: -0.0000

Data Index: 324364 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6914. Min Act: -0.0001

Data Index: 1251876 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6633. Min Act: -0.0000

Data Index: 259257 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.7026. Min Act: -0.0001

Data Index: 478742 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6583. Min Act: -0.0000

Data Index: 274168 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6769. Min Act: -0.0001

Data Index: 944366 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6486. Min Act: -0.0001

Data Index: 274924 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6658. Min Act: -0.0001

Data Index: 1329050 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6831. Min Act: -0.0000

Data Index: 130422 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6609. Min Act: -0.0001

Data Index: 533498 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.7170. Min Act: -0.0001

Data Index: 194283 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6983. Min Act: -0.0001

Data Index: 929149 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6226. Min Act: -0.0001

Data Index: 653578 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6241. Min Act: -0.0001

Data Index: 558898 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6230. Min Act: -0.0001

Data Index: 1316605 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6216. Min Act: -0.0001

Data Index: 214082 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.1035. Min Range: -1.1035

Max Act: 0.6499. Min Act: -0.0001

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 998