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

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

Neuron 5913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0216. Min Range: -4.0216

Max Act: 4.0216. Min Act: -0.0000

Data Index: 1501579 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.5512. Min Act: -0.0000

Data Index: 1385595 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.4433. Min Act: -0.0000

Data Index: 1509250 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.1778. Min Act: -0.0000

Data Index: 1394422 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.1527. Min Act: -0.0000

Data Index: 171456 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.0585. Min Act: -0.0000

Data Index: 1521048 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 4.0216. Min Range: -4.0216

Max Act: 3.0524. Min Act: -0.0000

Data Index: 1618119 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8935. Min Act: -0.0000

Data Index: 1504246 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.9845. Min Act: -0.0000

Data Index: 1613957 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8240. Min Act: -0.0000

Data Index: 1165106 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.9857. Min Act: -0.0000

Data Index: 1383105 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8209. Min Act: -0.0000

Data Index: 1466807 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.7787. Min Act: -0.0000

Data Index: 1417717 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.9141. Min Act: -0.0000

Data Index: 1586516 (Python Code)

Max Activating Token Index: 542

Text #14

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.9140. Min Act: -0.0000

Data Index: 1439927 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.7116. Min Act: -0.0000

Data Index: 1385196 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8419. Min Act: -0.0000

Data Index: 1627206 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8058. Min Act: -0.0000

Data Index: 1122626 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.8044. Min Act: -0.0000

Data Index: 1444618 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 4.0216. Min Range: -4.0216

Max Act: 2.9299. Min Act: -0.0000

Data Index: 620527 (C4 (Web Text))

Max Activating Token Index: 973