Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0324. Min Range: -1.0324

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1583147 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1579211 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8980. Min Act: -0.0001

Data Index: 1407648 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8859. Min Act: -0.0001

Data Index: 332414 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1539766 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1536424 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8328. Min Act: -0.0001

Data Index: 1543414 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8590. Min Act: -0.0001

Data Index: 1425457 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1457088 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8451. Min Act: -0.0001

Data Index: 1633364 (Python Code)

Max Activating Token Index: 582

Text #10

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1648676 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8135. Min Act: -0.0001

Data Index: 1521311 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1641229 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1604505 (Python Code)

Max Activating Token Index: 468

Text #14

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8102. Min Act: -0.0001

Data Index: 1382173 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1515618 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1643251 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1577308 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1396118 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1501031 (Python Code)

Max Activating Token Index: 293