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

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

Neuron 330 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1572. Min Act: -0.0001

Data Index: 727563 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0001

Data Index: 127162 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1521. Min Act: -0.0001

Data Index: 884120 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1333715 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1497. Min Act: -0.0001

Data Index: 131640 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1416. Min Act: -0.0001

Data Index: 290989 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1402. Min Act: -0.0001

Data Index: 421738 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1343. Min Act: -0.0001

Data Index: 986590 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1218998 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1337823 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1227193 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1261. Min Act: -0.0001

Data Index: 942794 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1112. Min Act: -0.0001

Data Index: 413470 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1111. Min Act: -0.0001

Data Index: 970912 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1645393 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1256. Min Act: -0.0001

Data Index: 431154 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1125014 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1553633 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1115. Min Act: -0.0001

Data Index: 958127 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1023. Min Act: -0.0001

Data Index: 294552 (C4 (Web Text))

Max Activating Token Index: 863