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

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

Neuron 1959 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1457. Min Act: -0.0002

Data Index: 435214 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1333949 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1505974 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1400. Min Act: -0.0002

Data Index: 446778 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1378. Min Act: -0.0002

Data Index: 876385 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1351. Min Act: -0.0002

Data Index: 445697 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1187. Min Act: -0.0002

Data Index: 947904 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1339. Min Act: -0.0001

Data Index: 331793 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1253. Min Act: -0.0001

Data Index: 509683 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1059465 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1357156 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1347737 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1270. Min Act: -0.0001

Data Index: 271302 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1184120 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1458883 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1256516 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1586785 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1123. Min Act: -0.0001

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1064. Min Act: -0.0002

Data Index: 28255 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1129. Min Act: -0.0002

Data Index: 861558 (C4 (Web Text))

Max Activating Token Index: 592