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

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

Neuron 5359 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: 0.8391. Min Range: -0.8391

Max Act: 0.7965. Min Act: -0.0000

Data Index: 559698 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8155. Min Act: -0.0000

Data Index: 89276 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1350153 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7273. Min Act: -0.0000

Data Index: 724247 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7924. Min Act: -0.0000

Data Index: 235083 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8085. Min Act: -0.0000

Data Index: 394583 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1340687 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7777. Min Act: -0.0000

Data Index: 749490 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1165229 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7446. Min Act: -0.0000

Data Index: 18457 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7866. Min Act: -0.0001

Data Index: 208430 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7048. Min Act: -0.0000

Data Index: 499854 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6853. Min Act: -0.0000

Data Index: 185560 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7428. Min Act: -0.0000

Data Index: 168575 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8045. Min Act: -0.0000

Data Index: 499940 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8031. Min Act: -0.0000

Data Index: 307119 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6927. Min Act: -0.0001

Data Index: 811125 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6696. Min Act: -0.0000

Data Index: 984917 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7190. Min Act: -0.0000

Data Index: 880492 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1155147 (C4 (Web Text))

Max Activating Token Index: 359