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

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

Neuron 4280 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.2330. Min Act: -0.0000

Data Index: 332742 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1609518 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1364561 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1645763 (Python Code)

Max Activating Token Index: 82

Text #4

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1636383 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1518445 (Python Code)

Max Activating Token Index: 883

Text #6

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1382130 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1623615 (Python Code)

Max Activating Token Index: 375

Text #8

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1517943 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1561895 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1650066 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9189. Min Act: -0.0000

Data Index: 55917 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1529247 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 1.2330. Min Range: -1.2330

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1633711 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9184. Min Act: -0.0000

Data Index: 76234 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1047625 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1630590 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1392595 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1402479 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 1.2330. Min Range: -1.2330

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1545079 (Python Code)

Max Activating Token Index: 292