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

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

Neuron 4522 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: 0.1778. Min Range: -0.1778

Max Act: 0.1778. Min Act: -0.0000

Data Index: 62528 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1631104 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1332. Min Act: -0.0000

Data Index: 186104 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1346670 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1404353 (Python Code)

Max Activating Token Index: 484

Text #5

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1085247 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1221. Min Act: -0.0000

Data Index: 751846 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1223. Min Act: -0.0000

Data Index: 751330 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1415878 (Python Code)

Max Activating Token Index: 507

Text #9

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1406220 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1510820 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1440040 (Python Code)

Max Activating Token Index: 583

Text #12

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1559568 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1133. Min Act: -0.0000

Data Index: 533025 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1031646 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1090. Min Act: -0.0000

Data Index: 256662 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1076. Min Act: -0.0000

Data Index: 596455 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1480234 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1570572 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1071. Min Act: -0.0000

Data Index: 291329 (C4 (Web Text))

Max Activating Token Index: 376