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

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

Neuron 1394 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6459. Min Act: -0.0000

Data Index: 301374 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1280086 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.7018. Min Act: 0.0000

Data Index: 642174 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5596. Min Act: -0.0000

Data Index: 405636 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6033. Min Act: -0.0000

Data Index: 900891 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6368. Min Act: -0.0000

Data Index: 776090 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5673. Min Act: -0.0000

Data Index: 391564 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1234979 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6075. Min Act: -0.0000

Data Index: 440098 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1293802 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5793. Min Act: -0.0000

Data Index: 401426 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5721. Min Act: -0.0000

Data Index: 517765 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1225748 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5206. Min Act: -0.0000

Data Index: 366426 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1102000 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.4790. Min Act: -0.0000

Data Index: 386434 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.4959. Min Act: -0.0000

Data Index: 339033 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5115. Min Act: -0.0000

Data Index: 875956 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.4042. Min Act: -0.0000

Data Index: 931897 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.4634. Min Act: -0.0000

Data Index: 565107 (C4 (Web Text))

Max Activating Token Index: 606