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

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

Neuron 4972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.8167. Min Act: -0.0002

Data Index: 1637867 (Python Code)

Max Activating Token Index: 891

Text #1

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6984. Min Act: -0.0002

Data Index: 1453201 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6064. Min Act: -0.0002

Data Index: 1607165 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6544. Min Act: -0.0002

Data Index: 1595404 (Python Code)

Max Activating Token Index: 265

Text #4

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6452. Min Act: -0.0002

Data Index: 1550871 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6240. Min Act: -0.0002

Data Index: 1577736 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5558. Min Act: -0.0002

Data Index: 1397947 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.4889. Min Act: -0.0002

Data Index: 1374330 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5342. Min Act: -0.0002

Data Index: 1487280 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5118. Min Act: -0.0002

Data Index: 1628385 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6210. Min Act: -0.0002

Data Index: 1631350 (Python Code)

Max Activating Token Index: 445

Text #11

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5470. Min Act: -0.0002

Data Index: 1380155 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5264. Min Act: -0.0002

Data Index: 1497024 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5629. Min Act: -0.0002

Data Index: 1376325 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5622. Min Act: -0.0002

Data Index: 1408616 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5296. Min Act: -0.0002

Data Index: 1517262 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5744. Min Act: -0.0002

Data Index: 1420950 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5920. Min Act: -0.0002

Data Index: 1396360 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5443. Min Act: -0.0002

Data Index: 1411563 (Python Code)

Max Activating Token Index: 434

Text #19

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5183. Min Act: -0.0002

Data Index: 1642621 (Python Code)

Max Activating Token Index: 152