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

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

Neuron 2314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2543. Min Act: -0.0000

Data Index: 836827 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0001

Data Index: 941299 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2498. Min Act: -0.0000

Data Index: 37877 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1098375 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1133736 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1123562 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2407. Min Act: -0.0001

Data Index: 592400 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2184. Min Act: -0.0000

Data Index: 307080 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2055. Min Act: -0.0000

Data Index: 564982 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1348631 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2154. Min Act: -0.0000

Data Index: 425706 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1267148 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2146. Min Act: -0.0000

Data Index: 264656 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1238399 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2235. Min Act: -0.0000

Data Index: 554922 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2070. Min Act: -0.0000

Data Index: 48905 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2077. Min Act: -0.0000

Data Index: 468774 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2010. Min Act: -0.0000

Data Index: 308350 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2055. Min Act: -0.0000

Data Index: 531430 (C4 (Web Text))

Max Activating Token Index: 256