Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.3249. Min Act: -0.0000

Data Index: 511338 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2754. Min Act: -0.0000

Data Index: 122320 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1255216 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1285469 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2279. Min Act: -0.0001

Data Index: 247829 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2298. Min Act: -0.0001

Data Index: 766907 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2323. Min Act: -0.0000

Data Index: 423325 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2228. Min Act: -0.0001

Data Index: 342979 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2389. Min Act: -0.0000

Data Index: 395899 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2267. Min Act: -0.0000

Data Index: 234275 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2214. Min Act: -0.0000

Data Index: 282773 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1323483 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2140. Min Act: 0.0000

Data Index: 859506 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2191. Min Act: -0.0000

Data Index: 152584 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1165847 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.2057. Min Act: -0.0000

Data Index: 467302 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1980. Min Act: -0.0000

Data Index: 993736 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1944. Min Act: -0.0000

Data Index: 10422 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1863. Min Act: -0.0001

Data Index: 494933 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1938. Min Act: -0.0000

Data Index: 541597 (C4 (Web Text))

Max Activating Token Index: 298