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

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

Neuron 745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1508522 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1399247 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1371. Min Act: -0.0001

Data Index: 84848 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1354. Min Act: -0.0001

Data Index: 428144 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1472992 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1496640 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1537810 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1247815 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1037430 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1152. Min Act: -0.0001

Data Index: 850088 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1420156 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1431644 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1135. Min Act: -0.0001

Data Index: 480657 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1417042 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1295064 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1403110 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1220. Min Act: -0.0001

Data Index: 904996 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1591301 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1367405 (Python Code)

Max Activating Token Index: 961

Text #19

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1111. Min Act: -0.0001

Data Index: 55631 (C4 (Web Text))

Max Activating Token Index: 780