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

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

Neuron 2679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.7243. Min Act: -0.0000

Data Index: 1593765 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.2429. Min Act: -0.0000

Data Index: 341534 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.5938. Min Act: -0.0000

Data Index: 1621777 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0590. Min Act: -0.0000

Data Index: 477805 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1691. Min Act: -0.0000

Data Index: 285232 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1587882 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0079. Min Act: -0.0000

Data Index: 1446623 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1972. Min Act: -0.0000

Data Index: 1481649 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1412284 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1278. Min Act: -0.0000

Data Index: 1517091 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1094. Min Act: -0.0000

Data Index: 1650252 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1108. Min Act: -0.0000

Data Index: 1620745 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1458465 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0913. Min Act: -0.0000

Data Index: 1265849 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1385735 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 2.7243. Min Range: -2.7243

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1547556 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 2.7243. Min Range: -2.7243

Max Act: 1.9195. Min Act: -0.0000

Data Index: 1464715 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1376348 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 2.7243. Min Range: -2.7243

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1478470 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 2.7243. Min Range: -2.7243

Max Act: 2.0184. Min Act: -0.0000

Data Index: 1575248 (Python Code)

Max Activating Token Index: 207