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

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

Neuron 4178 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.1671. Min Act: -0.0000

Data Index: 717271 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.0771. Min Act: -0.0000

Data Index: 418103 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.0824. Min Act: -0.0000

Data Index: 298006 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.1294. Min Act: -0.0000

Data Index: 863066 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.0781. Min Act: -0.0000

Data Index: 973387 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.0758. Min Act: -0.0000

Data Index: 118254 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9253. Min Act: -0.0000

Data Index: 82084 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 2.1671. Min Range: -2.1671

Max Act: 2.0857. Min Act: -0.0000

Data Index: 630761 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9171. Min Act: -0.0000

Data Index: 749401 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9251. Min Act: -0.0000

Data Index: 944517 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.8747. Min Act: -0.0000

Data Index: 329639 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9173. Min Act: -0.0000

Data Index: 553442 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.8642. Min Act: -0.0000

Data Index: 705560 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9153. Min Act: -0.0000

Data Index: 647220 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9187. Min Act: -0.0000

Data Index: 125554 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9106. Min Act: -0.0000

Data Index: 474418 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9525. Min Act: -0.0000

Data Index: 344424 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.8875. Min Act: -0.0000

Data Index: 582602 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.9140. Min Act: -0.0000

Data Index: 251382 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.1671. Min Range: -2.1671

Max Act: 1.8069. Min Act: -0.0000

Data Index: 677254 (C4 (Web Text))

Max Activating Token Index: 158