Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0006

Data Index: 247802 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0314. Min Act: -0.0006

Data Index: 181106 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0344. Min Act: -0.0006

Data Index: 873355 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0311. Min Act: -0.0006

Data Index: 786995 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0329. Min Act: -0.0006

Data Index: 391512 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0301. Min Act: -0.0006

Data Index: 86961 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0308. Min Act: -0.0006

Data Index: 427022 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1323651 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0305. Min Act: -0.0006

Data Index: 409380 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0291. Min Act: -0.0006

Data Index: 295193 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0314. Min Act: -0.0005

Data Index: 87989 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0306. Min Act: -0.0006

Data Index: 924809 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1166202 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1045779 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0304. Min Act: -0.0006

Data Index: 600527 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0281. Min Act: -0.0006

Data Index: 734620 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0286. Min Act: -0.0006

Data Index: 9075 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0265. Min Act: -0.0006

Data Index: 372120 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0294. Min Act: -0.0005

Data Index: 897089 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0292. Min Act: -0.0006

Data Index: 247504 (C4 (Web Text))

Max Activating Token Index: 34