Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 88 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1487880 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1434284 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0454. Min Act: -0.0000

Data Index: 352194 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1372332 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1048040 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1057598 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0380. Min Act: -0.0000

Data Index: 901998 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1531773 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1377399 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1517478 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1447497 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0299. Min Act: -0.0000

Data Index: 5141 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1472085 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1200156 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1427583 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1637210 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1609107 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1243634 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1399414 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1608388 (Python Code)

Max Activating Token Index: 122