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

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

Neuron 6027 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2828. Min Range: -4.2828

Max Act: 4.2828. Min Act: -0.0000

Data Index: 511391 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 4.2828. Min Range: -4.2828

Max Act: 4.0157. Min Act: -0.0000

Data Index: 377326 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6006. Min Act: -0.0000

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6997. Min Act: -0.0000

Data Index: 1181338 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6652. Min Act: -0.0000

Data Index: 150741 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.4798. Min Act: -0.0000

Data Index: 1510588 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.8169. Min Act: -0.0000

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6440. Min Act: -0.0000

Data Index: 1058599 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.4371. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6004. Min Act: -0.0000

Data Index: 203040 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.5453. Min Act: -0.0000

Data Index: 429159 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.5436. Min Act: -0.0000

Data Index: 590299 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.5404. Min Act: -0.0000

Data Index: 1226096 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6922. Min Act: -0.0000

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.5117. Min Act: -0.0000

Data Index: 782749 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6546. Min Act: -0.0000

Data Index: 223653 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.4832. Min Act: -0.0000

Data Index: 671866 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.4957. Min Act: -0.0000

Data Index: 1045688 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.6396. Min Act: -0.0000

Data Index: 118971 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 4.2828. Min Range: -4.2828

Max Act: 3.4306. Min Act: -0.0000

Data Index: 1108652 (C4 (Web Text))

Max Activating Token Index: 742