Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8617. Min Range: -3.8617

Max Act: 3.8617. Min Act: -0.0001

Data Index: 288845 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.3513. Min Act: -0.0001

Data Index: 953038 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.2079. Min Act: -0.0001

Data Index: 854830 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.2045. Min Act: -0.0001

Data Index: 109609 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.2659. Min Act: -0.0001

Data Index: 442577 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.2628. Min Act: -0.0001

Data Index: 164151 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.2265. Min Act: -0.0001

Data Index: 132280 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.1659. Min Act: -0.0001

Data Index: 120775 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.9966. Min Act: -0.0001

Data Index: 737784 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.0554. Min Act: -0.0001

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.0597. Min Act: -0.0001

Data Index: 524685 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.0474. Min Act: -0.0001

Data Index: 267338 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.1094. Min Act: -0.0001

Data Index: 1181377 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.8806. Min Act: -0.0001

Data Index: 1098838 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.9950. Min Act: -0.0001

Data Index: 1154680 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.8516. Min Act: -0.0001

Data Index: 1176589 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.8489. Min Act: -0.0001

Data Index: 746574 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.8617. Min Range: -3.8617

Max Act: 2.0466. Min Act: -0.0001

Data Index: 974519 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.9437. Min Act: -0.0001

Data Index: 209882 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.8617. Min Range: -3.8617

Max Act: 1.8200. Min Act: -0.0001

Data Index: 1204895 (C4 (Web Text))

Max Activating Token Index: 724