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

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

Neuron 3393 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1361200 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1529574 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1480752 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7284. Min Act: -0.0000

Data Index: 554245 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1485331 (Python Code)

Max Activating Token Index: 397

Text #5

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6735. Min Act: -0.0000

Data Index: 472277 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1466437 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1636279 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1445440 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1645116 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1362435 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6281. Min Act: -0.0000

Data Index: 901402 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1445901 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1623444 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1410146 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1528876 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6038. Min Act: -0.0000

Data Index: 761441 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1489900 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1593666 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6176. Min Act: -0.0000

Data Index: 112821 (C4 (Web Text))

Max Activating Token Index: 299