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

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

Neuron 624 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.9727. Min Act: -0.0001

Data Index: 744277 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.4435. Min Act: -0.0001

Data Index: 1524424 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.2661. Min Act: -0.0000

Data Index: 1419085 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.9101. Min Act: -0.0000

Data Index: 1373999 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.8208. Min Act: -0.0000

Data Index: 782394 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.0290. Min Act: -0.0000

Data Index: 951953 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.0434. Min Act: -0.0000

Data Index: 270431 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.3397. Min Act: -0.0000

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.0710. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.7465. Min Act: -0.0000

Data Index: 899430 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.8202. Min Act: -0.0000

Data Index: 400874 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.1339. Min Act: -0.0000

Data Index: 71746 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.9406. Min Act: -0.0000

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.0897. Min Act: -0.0001

Data Index: 243060 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.7853. Min Act: -0.0000

Data Index: 535672 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.9176. Min Act: -0.0000

Data Index: 805047 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.4259. Min Act: -0.0001

Data Index: 102483 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.7134. Min Act: -0.0000

Data Index: 300475 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.8837. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 5.9727. Min Range: -5.9727

Max Act: 4.8203. Min Act: -0.0000

Data Index: 736330 (C4 (Web Text))

Max Activating Token Index: 900