Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0400. Min Range: -1.0400

Max Act: 1.0400. Min Act: 0.0000

Data Index: 1457182 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1552141 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1474768 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8847. Min Act: 0.0000

Data Index: 1609167 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1394504 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1619691 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1649845 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1403630 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1590712 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1558310 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8654. Min Act: 0.0001

Data Index: 1517817 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1584280 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8502. Min Act: 0.0002

Data Index: 1556751 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1413170 (Python Code)

Max Activating Token Index: 511

Text #14

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1489601 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8116. Min Act: 0.0000

Data Index: 1384740 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1454297 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1468704 (Python Code)

Max Activating Token Index: 416

Text #18

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1418544 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8154. Min Act: -0.0000

Data Index: 309274 (C4 (Web Text))

Max Activating Token Index: 857