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

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

Neuron 5451 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.7008. Min Act: -0.0000

Data Index: 938891 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.6206. Min Act: -0.0000

Data Index: 1368473 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.6868. Min Act: -0.0000

Data Index: 404256 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.6252. Min Act: -0.0000

Data Index: 716534 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2298. Min Act: -0.0000

Data Index: 220097 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.4103. Min Act: -0.0000

Data Index: 1518343 (Python Code)

Max Activating Token Index: 418

Text #6

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2546. Min Act: -0.0000

Data Index: 1538306 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2279. Min Act: -0.0000

Data Index: 891323 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2208. Min Act: -0.0000

Data Index: 77127 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1502982 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.2761. Min Act: -0.0000

Data Index: 587665 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1310. Min Act: -0.0000

Data Index: 1180549 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1650089 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1847. Min Act: -0.0000

Data Index: 412069 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.0545. Min Act: -0.0000

Data Index: 25402 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1545. Min Act: -0.0000

Data Index: 142418 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1649. Min Act: -0.0000

Data Index: 1617815 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.0421. Min Act: -0.0000

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1495. Min Act: -0.0000

Data Index: 450409 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 2.7008. Min Range: -2.7008

Max Act: 2.1161. Min Act: -0.0000

Data Index: 1432512 (Python Code)

Max Activating Token Index: 13