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

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

Neuron 3343 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: 2.9109. Min Range: -2.9109

Max Act: 2.9109. Min Act: -0.0000

Data Index: 1389536 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 2.9109. Min Range: -2.9109

Max Act: 2.4027. Min Act: -0.0000

Data Index: 1431419 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 2.9109. Min Range: -2.9109

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1365060 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8720. Min Act: -0.0000

Data Index: 1578935 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1401436 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1463670 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1438803 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8789. Min Act: -0.0000

Data Index: 1517161 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.6547. Min Act: -0.0000

Data Index: 1612303 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1592401 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8257. Min Act: -0.0000

Data Index: 1372127 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8840. Min Act: -0.0000

Data Index: 1472596 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.7802. Min Act: -0.0000

Data Index: 1597037 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8769. Min Act: -0.0000

Data Index: 1395488 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.8527. Min Act: -0.0000

Data Index: 1445765 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1430840 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1406795 (Python Code)

Max Activating Token Index: 515

Text #17

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1515511 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1361708 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 2.9109. Min Range: -2.9109

Max Act: 1.3994. Min Act: -0.0000

Data Index: 1648473 (Python Code)

Max Activating Token Index: 160