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

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

Neuron 4728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6543. Min Act: -0.0000

Data Index: 579635 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6242. Min Act: -0.0000

Data Index: 40570 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5579. Min Act: -0.0000

Data Index: 904458 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1089838 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5192. Min Act: -0.0000

Data Index: 691704 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5151. Min Act: -0.0000

Data Index: 777758 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5148. Min Act: -0.0000

Data Index: 22562 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5121. Min Act: -0.0000

Data Index: 414359 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4833. Min Act: -0.0000

Data Index: 29931 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4696. Min Act: -0.0000

Data Index: 851958 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5065. Min Act: -0.0000

Data Index: 887620 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4875. Min Act: -0.0000

Data Index: 630740 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5053. Min Act: -0.0000

Data Index: 12662 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5044. Min Act: -0.0000

Data Index: 443854 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1160907 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4534. Min Act: -0.0000

Data Index: 852857 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4786. Min Act: -0.0000

Data Index: 683845 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4963. Min Act: -0.0000

Data Index: 800254 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4785. Min Act: -0.0000

Data Index: 987855 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4634. Min Act: -0.0000

Data Index: 14371 (C4 (Web Text))

Max Activating Token Index: 318