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

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

Neuron 3604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1190487 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1471. Min Act: -0.0000

Data Index: 237334 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1135601 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1358305 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1183. Min Act: -0.0000

Data Index: 504313 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1299948 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1315. Min Act: -0.0000

Data Index: 808482 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1214. Min Act: -0.0000

Data Index: 295414 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1230. Min Act: -0.0000

Data Index: 259941 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1257. Min Act: -0.0000

Data Index: 829321 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1260. Min Act: -0.0000

Data Index: 556075 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1581814 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1237. Min Act: -0.0000

Data Index: 892769 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.0984. Min Act: -0.0000

Data Index: 35060 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1180. Min Act: -0.0000

Data Index: 134546 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1128. Min Act: -0.0000

Data Index: 211973 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1127718 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1148. Min Act: -0.0000

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1018. Min Act: -0.0000

Data Index: 786272 (C4 (Web Text))

Max Activating Token Index: 622