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

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

Neuron 2481 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1516812 (Python Code)

Max Activating Token Index: 590

Text #1

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1544576 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1497194 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1436665 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1611782 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1385153 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1635118 (Python Code)

Max Activating Token Index: 579

Text #7

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1553715 (Python Code)

Max Activating Token Index: 623

Text #8

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1431904 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1376329 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1506210 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1362997 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1369738 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1444260 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1572373 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1619026 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1489187 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1385545 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1602261 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1633814 (Python Code)

Max Activating Token Index: 159