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

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

Neuron 2334 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1395432 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1369366 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9104. Min Act: -0.0001

Data Index: 1565412 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1409665 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1504252 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1433138 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7948. Min Act: -0.0000

Data Index: 317901 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1489212 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1563201 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1645877 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1630617 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1618389 (Python Code)

Max Activating Token Index: 939

Text #12

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1613496 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6979. Min Act: -0.0001

Data Index: 1579233 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1496195 (Python Code)

Max Activating Token Index: 765

Text #15

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6161. Min Act: -0.0000

Data Index: 228533 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1400125 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1510271 (Python Code)

Max Activating Token Index: 610

Text #18

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1484194 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1493415 (Python Code)

Max Activating Token Index: 320