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

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

Neuron 5110 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0911. Min Act: -0.0000

Data Index: 971650 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.1414. Min Act: -0.0000

Data Index: 852578 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1040567 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0795. Min Act: -0.0000

Data Index: 408175 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0348. Min Act: -0.0000

Data Index: 312155 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9757. Min Act: -0.0000

Data Index: 889513 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0521. Min Act: -0.0000

Data Index: 954824 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9608. Min Act: -0.0000

Data Index: 776587 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1199083 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9099. Min Act: -0.0000

Data Index: 270996 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9240. Min Act: -0.0000

Data Index: 887887 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8739. Min Act: -0.0000

Data Index: 566150 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8673. Min Act: -0.0000

Data Index: 46012 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9462. Min Act: -0.0000

Data Index: 683970 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8772. Min Act: -0.0000

Data Index: 963061 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.7117. Min Act: -0.0000

Data Index: 942182 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8275. Min Act: -0.0000

Data Index: 331940 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8505. Min Act: -0.0000

Data Index: 426305 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8941. Min Act: -0.0000

Data Index: 752311 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8399. Min Act: -0.0000

Data Index: 418785 (C4 (Web Text))

Max Activating Token Index: 819