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

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

Neuron 6016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3899. Min Act: -0.0000

Data Index: 814268 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3170. Min Act: -0.0001

Data Index: 462222 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1819. Min Act: -0.0000

Data Index: 966427 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1194566 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0498. Min Act: -0.0000

Data Index: 277000 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1307522 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1240840 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1199. Min Act: -0.0000

Data Index: 253393 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1025699 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1099. Min Act: -0.0000

Data Index: 506042 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1303. Min Act: -0.0001

Data Index: 501141 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0417. Min Act: -0.0000

Data Index: 887207 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1022727 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0521. Min Act: -0.0001

Data Index: 321230 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1118. Min Act: -0.0001

Data Index: 521977 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0705. Min Act: -0.0000

Data Index: 133836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1009. Min Act: -0.0000

Data Index: 145402 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0657. Min Act: -0.0000

Data Index: 753471 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0592. Min Act: -0.0000

Data Index: 108625 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.9981. Min Act: -0.0000

Data Index: 688502 (C4 (Web Text))

Max Activating Token Index: 951