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

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

Neuron 1908 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: 3.7824. Min Range: -3.7824

Max Act: 3.7824. Min Act: 0.0000

Data Index: 1639177 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.4132. Min Act: 0.0001

Data Index: 1440883 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.2033. Min Act: 0.0001

Data Index: 1590737 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.1247. Min Act: 0.0001

Data Index: 1483545 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.9786. Min Act: 0.0000

Data Index: 1386316 (Python Code)

Max Activating Token Index: 168

Text #5

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.0798. Min Act: 0.0000

Data Index: 1517377 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.0862. Min Act: 0.0001

Data Index: 1524130 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.0055. Min Act: 0.0001

Data Index: 1598438 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 3.7824. Min Range: -3.7824

Max Act: 3.1272. Min Act: -0.0000

Data Index: 1375854 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.9185. Min Act: 0.0001

Data Index: 1640437 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.9114. Min Act: 0.0001

Data Index: 1450745 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.8974. Min Act: 0.0001

Data Index: 1380323 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.9326. Min Act: 0.0001

Data Index: 1588799 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.7653. Min Act: 0.0001

Data Index: 1562873 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.7520. Min Act: 0.0000

Data Index: 1415537 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.5941. Min Act: 0.0001

Data Index: 1412191 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.7203. Min Act: 0.0000

Data Index: 1403453 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.5657. Min Act: 0.0001

Data Index: 1501511 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.8340. Min Act: 0.0000

Data Index: 1401080 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 3.7824. Min Range: -3.7824

Max Act: 2.5571. Min Act: -0.0000

Data Index: 1426361 (Python Code)

Max Activating Token Index: 161