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

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

Neuron 5046 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0488. Min Act: -0.0000

Data Index: 913434 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.1223. Min Act: -0.0000

Data Index: 153226 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0399. Min Act: -0.0000

Data Index: 331267 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0078. Min Act: -0.0000

Data Index: 100541 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1167005 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0858. Min Act: -0.0000

Data Index: 681207 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0030. Min Act: -0.0000

Data Index: 858251 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0614. Min Act: -0.0000

Data Index: 920020 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1330815 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0147. Min Act: -0.0000

Data Index: 809274 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0238. Min Act: -0.0000

Data Index: 147823 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1280320 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0102. Min Act: -0.0000

Data Index: 962702 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9870. Min Act: -0.0000

Data Index: 546910 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0489. Min Act: -0.0000

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0408. Min Act: -0.0000

Data Index: 289738 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0445. Min Act: -0.0000

Data Index: 676424 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0664. Min Act: -0.0000

Data Index: 633432 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0274. Min Act: -0.0000

Data Index: 570814 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1161491 (C4 (Web Text))

Max Activating Token Index: 535