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

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

Neuron 3453 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: 2.9536. Min Range: -2.9536

Max Act: 2.9536. Min Act: -0.0000

Data Index: 544001 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.5442. Min Act: -0.0000

Data Index: 168108 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.1266. Min Act: -0.0000

Data Index: 770821 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1308056 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.1458. Min Act: -0.0000

Data Index: 765366 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.1112. Min Act: -0.0000

Data Index: 435496 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.0922. Min Act: -0.0000

Data Index: 7550 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.9148. Min Act: -0.0000

Data Index: 626155 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.0264. Min Act: -0.0000

Data Index: 562770 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.1290. Min Act: -0.0000

Data Index: 333014 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.8240. Min Act: -0.0000

Data Index: 678324 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1031857 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 2.9536. Min Range: -2.9536

Max Act: 2.0984. Min Act: -0.0000

Data Index: 364553 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1160975 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.9764. Min Act: -0.0000

Data Index: 383334 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.9558. Min Act: -0.0000

Data Index: 862612 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.8434. Min Act: -0.0000

Data Index: 298132 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.9171. Min Act: -0.0000

Data Index: 915912 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.7870. Min Act: -0.0000

Data Index: 629877 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 2.9536. Min Range: -2.9536

Max Act: 1.8937. Min Act: -0.0000

Data Index: 1076591 (C4 (Web Text))

Max Activating Token Index: 185