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

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

Neuron 740 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1373340 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1378053 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1599872 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1637438 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1546. Min Act: -0.0000

Data Index: 917888 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1295598 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1680 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1383. Min Act: -0.0000

Data Index: 34274 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1486. Min Act: -0.0000

Data Index: 411448 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1314. Min Act: 0.0001

Data Index: 283969 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1308. Min Act: -0.0001

Data Index: 160820 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1154129 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1513126 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1341308 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1391961 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1247. Min Act: -0.0000

Data Index: 673674 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1196. Min Act: -0.0000

Data Index: 390567 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1640661 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1121. Min Act: -0.0000

Data Index: 918817 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1157877 (C4 (Web Text))

Max Activating Token Index: 229