Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2498 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1170657 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1543. Min Act: -0.0001

Data Index: 170064 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1464. Min Act: -0.0001

Data Index: 301750 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1517. Min Act: -0.0001

Data Index: 571362 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1152577 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1617823 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1272. Min Act: -0.0001

Data Index: 382109 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1375. Min Act: -0.0001

Data Index: 766536 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1113039 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1389890 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1625972 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1213983 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1346050 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.0955. Min Act: -0.0001

Data Index: 191894 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1284. Min Act: -0.0001

Data Index: 89668 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1197. Min Act: -0.0001

Data Index: 680530 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1148. Min Act: -0.0001

Data Index: 224052 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1245897 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1233. Min Act: -0.0001

Data Index: 913068 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1216. Min Act: -0.0001

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 800