Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 157 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5127. Min Act: -0.0001

Data Index: 326344 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1575626 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4717. Min Act: -0.0001

Data Index: 121472 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5394. Min Act: -0.0001

Data Index: 227938 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5411. Min Act: -0.0001

Data Index: 674599 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1089211 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5152. Min Act: -0.0001

Data Index: 1003988 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5336. Min Act: -0.0001

Data Index: 1363322 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1553577 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5334. Min Act: -0.0001

Data Index: 1385047 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4928. Min Act: -0.0001

Data Index: 691838 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4983. Min Act: -0.0001

Data Index: 90446 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5198. Min Act: -0.0001

Data Index: 535292 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1453115 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1046186 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4698. Min Act: -0.0001

Data Index: 816072 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4986. Min Act: -0.0001

Data Index: 684624 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4661. Min Act: -0.0001

Data Index: 1363886 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4568. Min Act: -0.0001

Data Index: 725793 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1503583 (Python Code)

Max Activating Token Index: 853