Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1704 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0003

Data Index: 1325014 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4982. Min Act: -0.0003

Data Index: 889645 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5001. Min Act: -0.0003

Data Index: 180836 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4758. Min Act: -0.0003

Data Index: 510888 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4590. Min Act: -0.0003

Data Index: 947984 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4538. Min Act: -0.0003

Data Index: 247005 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4631. Min Act: -0.0003

Data Index: 18758 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4324. Min Act: -0.0003

Data Index: 300142 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4245. Min Act: -0.0003

Data Index: 1089911 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4239. Min Act: -0.0003

Data Index: 318093 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4320. Min Act: -0.0003

Data Index: 77647 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4166. Min Act: -0.0003

Data Index: 1229330 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4140. Min Act: -0.0003

Data Index: 982448 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4066. Min Act: -0.0003

Data Index: 228858 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3834. Min Act: -0.0004

Data Index: 1299219 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3950. Min Act: -0.0003

Data Index: 1496338 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3892. Min Act: -0.0003

Data Index: 1228010 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3965. Min Act: -0.0003

Data Index: 672178 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3855. Min Act: -0.0003

Data Index: 427755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3829. Min Act: -0.0004

Data Index: 184551 (C4 (Web Text))

Max Activating Token Index: 458