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

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

Neuron 3158 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: 2.6679. Min Range: -2.6679

Max Act: 2.6679. Min Act: -0.0000

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 2.6679. Min Range: -2.6679

Max Act: 2.1958. Min Act: -0.0000

Data Index: 433447 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 2.6679. Min Range: -2.6679

Max Act: 2.1035. Min Act: -0.0000

Data Index: 716299 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.7834. Min Act: -0.0000

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.4983. Min Act: -0.0000

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1155. Min Act: -0.0000

Data Index: 354500 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1143. Min Act: -0.0000

Data Index: 499331 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1640. Min Act: -0.0000

Data Index: 322709 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.3404. Min Act: -0.0000

Data Index: 269324 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.2189. Min Act: -0.0000

Data Index: 164762 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1249617 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.2009. Min Act: -0.0000

Data Index: 375986 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.2046. Min Act: -0.0000

Data Index: 801786 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1331239 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1180. Min Act: -0.0000

Data Index: 258132 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1075528 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.1043. Min Act: -0.0000

Data Index: 693330 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1074708 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.0178. Min Act: -0.0000

Data Index: 323250 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.6679. Min Range: -2.6679

Max Act: 1.0488. Min Act: -0.0000

Data Index: 121627 (C4 (Web Text))

Max Activating Token Index: 483