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

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

Neuron 6138 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.3734. Min Act: -0.0000

Data Index: 130684 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.3288. Min Act: -0.0000

Data Index: 901573 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.3252. Min Act: -0.0000

Data Index: 892443 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.2187. Min Act: -0.0000

Data Index: 562895 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1359. Min Act: -0.0000

Data Index: 785954 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1193. Min Act: -0.0000

Data Index: 894527 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1342910 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1093395 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1246. Min Act: -0.0000

Data Index: 884634 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1261394 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1212. Min Act: -0.0000

Data Index: 903512 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1170. Min Act: -0.0000

Data Index: 513519 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1770. Min Act: -0.0000

Data Index: 813359 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1019. Min Act: -0.0000

Data Index: 230996 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1244865 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1114935 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1248282 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.0725. Min Act: -0.0000

Data Index: 15404 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.0732. Min Act: -0.0000

Data Index: 283972 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.3734. Min Range: -1.3734

Max Act: 1.0039. Min Act: -0.0000

Data Index: 636677 (C4 (Web Text))

Max Activating Token Index: 851