Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1087574 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1181. Min Act: -0.0000

Data Index: 599022 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0424. Min Act: -0.0000

Data Index: 891887 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0516. Min Act: -0.0000

Data Index: 469708 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0581. Min Act: -0.0000

Data Index: 73655 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1964. Min Act: -0.0000

Data Index: 535374 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9275. Min Act: -0.0000

Data Index: 893247 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9478. Min Act: -0.0000

Data Index: 107920 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1228324 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9426. Min Act: -0.0000

Data Index: 936005 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1204328 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1191252 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9427. Min Act: -0.0000

Data Index: 21200 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8995. Min Act: -0.0000

Data Index: 730282 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8691. Min Act: -0.0000

Data Index: 854280 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8987. Min Act: -0.0000

Data Index: 388120 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8942. Min Act: -0.0000

Data Index: 440023 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8443. Min Act: -0.0000

Data Index: 901593 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8660. Min Act: -0.0000

Data Index: 275748 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8348. Min Act: -0.0000

Data Index: 963222 (C4 (Web Text))

Max Activating Token Index: 46