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

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

Neuron 3034 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: 0.2607. Min Range: -0.2607

Max Act: 0.2520. Min Act: -0.0002

Data Index: 1491917 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2597. Min Act: -0.0002

Data Index: 1522551 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2326. Min Act: -0.0002

Data Index: 1467337 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2319. Min Act: -0.0002

Data Index: 1581274 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2536. Min Act: -0.0002

Data Index: 1483773 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2374. Min Act: -0.0002

Data Index: 1511610 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2607. Min Act: -0.0002

Data Index: 1464645 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2305. Min Act: -0.0002

Data Index: 1373125 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2268. Min Act: -0.0002

Data Index: 1636006 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2438. Min Act: -0.0002

Data Index: 1408747 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2335. Min Act: -0.0002

Data Index: 1368387 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1897. Min Act: -0.0002

Data Index: 1644557 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2174. Min Act: -0.0002

Data Index: 1651313 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2125. Min Act: -0.0002

Data Index: 1535989 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2103. Min Act: -0.0002

Data Index: 1415397 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2132. Min Act: -0.0002

Data Index: 1449115 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1868. Min Act: -0.0002

Data Index: 1403983 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1951. Min Act: -0.0002

Data Index: 1401233 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1940. Min Act: -0.0002

Data Index: 1428640 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2160. Min Act: -0.0002

Data Index: 1600881 (Python Code)

Max Activating Token Index: 9