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

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

Neuron 971 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1523051 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.6018. Min Act: -0.0000

Data Index: 804004 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5579. Min Act: -0.0000

Data Index: 1638050 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1468980 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1441721 (Python Code)

Max Activating Token Index: 804

Text #5

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5889. Min Act: -0.0000

Data Index: 1360477 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1637880 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1568364 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1539139 (Python Code)

Max Activating Token Index: 744

Text #9

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1500660 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1378527 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1508402 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1620740 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1408064 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1534080 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4345. Min Act: -0.0000

Data Index: 857585 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1517021 (Python Code)

Max Activating Token Index: 526

Text #17

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1474745 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1610006 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 1.6228. Min Range: -1.6228

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1566533 (Python Code)

Max Activating Token Index: 394