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

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

Neuron 1203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5284. Min Range: -2.5284

Max Act: 2.5284. Min Act: -0.0000

Data Index: 1454418 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 2.5284. Min Range: -2.5284

Max Act: 2.3489. Min Act: -0.0000

Data Index: 1569013 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 2.5284. Min Range: -2.5284

Max Act: 2.1228. Min Act: -0.0000

Data Index: 1579089 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 2.5284. Min Range: -2.5284

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1415300 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.9740. Min Act: -0.0000

Data Index: 1528079 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1652540 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1360050 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.8253. Min Act: -0.0000

Data Index: 1434281 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1520561 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.6390. Min Act: -0.0000

Data Index: 1385758 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1379239 (Python Code)

Max Activating Token Index: 184

Text #11

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1615802 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1654813 (Python Code)

Max Activating Token Index: 697

Text #13

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.8955. Min Act: -0.0000

Data Index: 1636132 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1495918 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.7724. Min Act: -0.0000

Data Index: 1455822 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1415240 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1465879 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1591953 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 2.5284. Min Range: -2.5284

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1455571 (Python Code)

Max Activating Token Index: 795