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

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

Neuron 4619 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: 0.5530. Min Range: -0.5530

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1399754 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1577695 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1386097 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1419259 (Python Code)

Max Activating Token Index: 270

Text #4

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1434262 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4720. Min Act: -0.0000

Data Index: 467384 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1399249 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1374810 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1264507 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4173. Min Act: -0.0000

Data Index: 586490 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4197. Min Act: -0.0000

Data Index: 989584 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4195. Min Act: -0.0000

Data Index: 457145 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4015. Min Act: -0.0000

Data Index: 891068 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4126. Min Act: -0.0000

Data Index: 42744 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1398526 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1396475 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.4096. Min Act: -0.0000

Data Index: 147151 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1218397 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.3695. Min Act: -0.0000

Data Index: 29878 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.5530. Min Range: -0.5530

Max Act: 0.3701. Min Act: -0.0000

Data Index: 283450 (C4 (Web Text))

Max Activating Token Index: 1008