Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1491637 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1372139 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1453247 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1580275 (Python Code)

Max Activating Token Index: 525

Text #4

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1546. Min Act: -0.0000

Data Index: 522692 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1498. Min Act: -0.0000

Data Index: 766076 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1196975 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1579546 (Python Code)

Max Activating Token Index: 841

Text #8

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1337. Min Act: -0.0000

Data Index: 249072 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1037301 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1368. Min Act: -0.0000

Data Index: 641132 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1274. Min Act: -0.0001

Data Index: 686403 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1258. Min Act: -0.0001

Data Index: 637388 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1214. Min Act: -0.0001

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1168. Min Act: -0.0000

Data Index: 979016 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1230. Min Act: -0.0000

Data Index: 124986 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1203176 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1228. Min Act: -0.0000

Data Index: 11759 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.1187. Min Act: -0.0000

Data Index: 935293 (C4 (Web Text))

Max Activating Token Index: 825