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

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

Neuron 2994 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: 0.1262. Min Range: -0.1262

Max Act: 0.1262. Min Act: -0.0001

Data Index: 650252 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1090508 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1217. Min Act: -0.0001

Data Index: 361003 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1128. Min Act: -0.0001

Data Index: 883269 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1303450 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1089. Min Act: -0.0001

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1042. Min Act: -0.0001

Data Index: 319456 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0958. Min Act: -0.0001

Data Index: 840006 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0993. Min Act: -0.0001

Data Index: 128346 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1031. Min Act: -0.0001

Data Index: 39768 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1014. Min Act: -0.0001

Data Index: 961840 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0989. Min Act: -0.0001

Data Index: 47737 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1024. Min Act: -0.0001

Data Index: 471641 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0938. Min Act: -0.0001

Data Index: 879040 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1181268 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0992. Min Act: -0.0001

Data Index: 748315 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0908. Min Act: -0.0001

Data Index: 399207 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0936. Min Act: -0.0001

Data Index: 96782 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1055739 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0925. Min Act: -0.0001

Data Index: 595547 (C4 (Web Text))

Max Activating Token Index: 445