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

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

Neuron 1006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3636. Min Range: -4.3636

Max Act: 4.3636. Min Act: -0.0001

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.6515. Min Act: -0.0001

Data Index: 1180245 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.5923. Min Act: -0.0000

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.7770. Min Act: -0.0001

Data Index: 644547 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.4635. Min Act: -0.0001

Data Index: 1248720 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.2716. Min Act: -0.0001

Data Index: 692513 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.3999. Min Act: -0.0001

Data Index: 1037020 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.5478. Min Act: -0.0001

Data Index: 146443 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.4508. Min Act: -0.0001

Data Index: 149496 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.4094. Min Act: -0.0001

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.1136. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 4.3636. Min Range: -4.3636

Max Act: 2.9513. Min Act: -0.0001

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.3798. Min Act: -0.0001

Data Index: 592638 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.3297. Min Act: -0.0001

Data Index: 916628 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.0891. Min Act: -0.0001

Data Index: 644615 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.1083. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.0263. Min Act: -0.0001

Data Index: 787519 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 4.3636. Min Range: -4.3636

Max Act: 2.8840. Min Act: -0.0001

Data Index: 955122 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.0045. Min Act: -0.0001

Data Index: 64811 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 4.3636. Min Range: -4.3636

Max Act: 3.1139. Min Act: -0.0000

Data Index: 303470 (C4 (Web Text))

Max Activating Token Index: 1016