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

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

Neuron 339 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4144. Min Range: -5.4144

Max Act: 5.4144. Min Act: -0.0001

Data Index: 1572230 (Python Code)

Max Activating Token Index: 831

Text #1

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.8380. Min Act: -0.0001

Data Index: 1571894 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.5043. Min Act: -0.0001

Data Index: 1385669 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.5646. Min Act: -0.0001

Data Index: 1623434 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 5.4144. Min Range: -5.4144

Max Act: 2.8771. Min Act: -0.0001

Data Index: 1502407 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1365. Min Act: -0.0001

Data Index: 1417239 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1245. Min Act: -0.0001

Data Index: 187415 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.4283. Min Act: -0.0001

Data Index: 1418782 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1168. Min Act: -0.0001

Data Index: 1587526 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1185. Min Act: -0.0001

Data Index: 1614718 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.2886. Min Act: -0.0001

Data Index: 1654737 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 5.4144. Min Range: -5.4144

Max Act: 2.9877. Min Act: -0.0001

Data Index: 1618697 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.2188. Min Act: -0.0001

Data Index: 1383643 (Python Code)

Max Activating Token Index: 396

Text #13

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1018. Min Act: -0.0001

Data Index: 773993 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.0733. Min Act: -0.0001

Data Index: 736714 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.1860. Min Act: -0.0001

Data Index: 1599942 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.0228. Min Act: -0.0001

Data Index: 383677 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 5.4144. Min Range: -5.4144

Max Act: 3.0095. Min Act: -0.0001

Data Index: 1415306 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 5.4144. Min Range: -5.4144

Max Act: 2.8702. Min Act: -0.0001

Data Index: 358684 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 5.4144. Min Range: -5.4144

Max Act: 2.8047. Min Act: -0.0001

Data Index: 1565641 (Python Code)

Max Activating Token Index: 131