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

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

Neuron 3905 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: 0.9913. Min Range: -0.9913

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1614496 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1386864 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1656243 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1368602 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1549895 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1581979 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1417194 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1650179 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1560922 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1444070 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1541172 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1473517 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1454359 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1370010 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1379013 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1602371 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1577455 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1404399 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1495434 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1566786 (Python Code)

Max Activating Token Index: 154