Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.8623. Min Act: -0.0000

Data Index: 905647 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1468476 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1471769 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1493985 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1160455 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6442. Min Act: -0.0000

Data Index: 267133 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6354. Min Act: -0.0000

Data Index: 874292 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1085328 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6252. Min Act: -0.0000

Data Index: 742919 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5930. Min Act: -0.0000

Data Index: 410551 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6253. Min Act: -0.0000

Data Index: 900578 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1154274 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5784. Min Act: -0.0000

Data Index: 584305 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6049. Min Act: -0.0000

Data Index: 963706 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6164. Min Act: -0.0000

Data Index: 43312 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1349435 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1203991 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5315. Min Act: -0.0000

Data Index: 582623 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5377. Min Act: -0.0000

Data Index: 26333 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5110. Min Act: -0.0000

Data Index: 605423 (C4 (Web Text))

Max Activating Token Index: 973