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

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

Neuron 2088 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0001

Data Index: 922596 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0324. Min Act: -0.0001

Data Index: 968233 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0288. Min Act: -0.0001

Data Index: 152169 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0239. Min Act: -0.0001

Data Index: 56757 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1343962 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0250. Min Act: -0.0001

Data Index: 902383 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0274. Min Act: -0.0001

Data Index: 283477 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0259. Min Act: -0.0001

Data Index: 428260 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0270. Min Act: -0.0001

Data Index: 104392 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1517915 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0250. Min Act: -0.0001

Data Index: 232075 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0239. Min Act: -0.0001

Data Index: 612940 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1259369 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0249. Min Act: -0.0001

Data Index: 382300 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1448977 (Python Code)

Max Activating Token Index: 730

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1627837 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0246. Min Act: -0.0001

Data Index: 281185 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0227. Min Act: -0.0001

Data Index: 858158 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1585401 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1624059 (Python Code)

Max Activating Token Index: 769