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

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

Neuron 4935 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.3892. Min Act: -0.0000

Data Index: 1167908 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.6602. Min Act: -0.0000

Data Index: 650300 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.3028. Min Act: -0.0000

Data Index: 1175670 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.3567. Min Act: -0.0000

Data Index: 434939 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.2994. Min Act: -0.0000

Data Index: 738454 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.0803. Min Act: -0.0000

Data Index: 352368 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.1761. Min Act: -0.0000

Data Index: 511497 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.1506. Min Act: -0.0000

Data Index: 895793 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.9759. Min Act: -0.0000

Data Index: 1229699 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.0523. Min Act: -0.0001

Data Index: 488946 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.2064. Min Act: -0.0000

Data Index: 1185054 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.6133. Min Act: -0.0000

Data Index: 779544 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.0076. Min Act: -0.0000

Data Index: 977074 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.8009. Min Act: -0.0000

Data Index: 990056 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 3.6602. Min Range: -3.6602

Max Act: 3.0504. Min Act: -0.0000

Data Index: 507925 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.9142. Min Act: -0.0000

Data Index: 247547 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.9145. Min Act: -0.0000

Data Index: 720103 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.6343. Min Act: -0.0000

Data Index: 96914 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.9065. Min Act: -0.0000

Data Index: 62191 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.6602. Min Range: -3.6602

Max Act: 2.8614. Min Act: -0.0000

Data Index: 77278 (C4 (Web Text))

Max Activating Token Index: 83