Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 106 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7690. Min Act: -0.0001

Data Index: 275104 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7683. Min Act: -0.0001

Data Index: 725982 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7114. Min Act: -0.0001

Data Index: 851605 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7139. Min Act: -0.0001

Data Index: 90462 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6066. Min Act: -0.0001

Data Index: 1050419 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5802. Min Act: -0.0001

Data Index: 960350 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6559. Min Act: -0.0001

Data Index: 1208449 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6506. Min Act: -0.0001

Data Index: 1105752 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6316. Min Act: -0.0001

Data Index: 510365 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7172. Min Act: -0.0001

Data Index: 691537 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.7142. Min Act: -0.0001

Data Index: 1350403 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6162. Min Act: -0.0001

Data Index: 4003 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6016. Min Act: -0.0001

Data Index: 113683 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5994. Min Act: -0.0001

Data Index: 579265 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5492. Min Act: -0.0001

Data Index: 126443 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.6875. Min Act: -0.0001

Data Index: 1322510 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.4641. Min Act: -0.0001

Data Index: 271441 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5782. Min Act: -0.0001

Data Index: 1231214 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5656. Min Act: -0.0001

Data Index: 817894 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.7690. Min Range: -1.7690

Max Act: 1.5720. Min Act: -0.0001

Data Index: 331480 (C4 (Web Text))

Max Activating Token Index: 310