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

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

Neuron 2012 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: 2.2222. Min Range: -2.2222

Max Act: 2.2222. Min Act: -0.0000

Data Index: 684929 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 2.2222. Min Range: -2.2222

Max Act: 1.4098. Min Act: -0.0000

Data Index: 585309 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.2222. Min Range: -2.2222

Max Act: 1.1375. Min Act: -0.0000

Data Index: 395964 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 2.2222. Min Range: -2.2222

Max Act: 1.0021. Min Act: -0.0000

Data Index: 294315 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 2.2222. Min Range: -2.2222

Max Act: 1.0232. Min Act: -0.0000

Data Index: 989224 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 2.2222. Min Range: -2.2222

Max Act: 1.0018. Min Act: -0.0000

Data Index: 14298 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.9193. Min Act: -0.0000

Data Index: 913467 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1258810 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1008132 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8663. Min Act: -0.0000

Data Index: 700678 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8177. Min Act: -0.0000

Data Index: 195638 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8192. Min Act: 0.0000

Data Index: 932912 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.7895. Min Act: -0.0000

Data Index: 797015 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8160. Min Act: 0.0001

Data Index: 1299133 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8075. Min Act: -0.0000

Data Index: 501332 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1202759 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.7340. Min Act: -0.0000

Data Index: 309381 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8004. Min Act: 0.0000

Data Index: 688868 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.8053. Min Act: 0.0000

Data Index: 667334 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 2.2222. Min Range: -2.2222

Max Act: 0.7982. Min Act: -0.0000

Data Index: 889646 (C4 (Web Text))

Max Activating Token Index: 231