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

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

Neuron 1881 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2500. Min Range: -2.2500

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1373214 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 2.2500. Min Range: -2.2500

Max Act: 2.2500. Min Act: -0.0000

Data Index: 1463520 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1384980 (Python Code)

Max Activating Token Index: 270

Text #3

Max Range: 2.2500. Min Range: -2.2500

Max Act: 2.1804. Min Act: -0.0000

Data Index: 1435557 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 2.2500. Min Range: -2.2500

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1532676 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 2.2500. Min Range: -2.2500

Max Act: 2.0187. Min Act: -0.0000

Data Index: 1608559 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.8612. Min Act: -0.0000

Data Index: 1576189 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1480835 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.9104. Min Act: -0.0001

Data Index: 1481466 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1518194 (Python Code)

Max Activating Token Index: 702

Text #11

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.6548. Min Act: -0.0000

Data Index: 1386036 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1519900 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1507909 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1500370 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1484656 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1621112 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1448683 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1530890 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 2.2500. Min Range: -2.2500

Max Act: 1.3241. Min Act: -0.0001

Data Index: 1419934 (Python Code)

Max Activating Token Index: 808