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

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

Neuron 4527 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: 3.7709. Min Range: -3.7709

Max Act: 3.7709. Min Act: -0.0000

Data Index: 21076 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 3.7709. Min Range: -3.7709

Max Act: 3.1099. Min Act: -0.0000

Data Index: 1028929 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6034. Min Act: -0.0000

Data Index: 1278605 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.3159. Min Act: -0.0000

Data Index: 1287402 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.8794. Min Act: -0.0000

Data Index: 977288 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.8079. Min Act: -0.0000

Data Index: 277051 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.7861. Min Act: -0.0000

Data Index: 832063 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.7817. Min Act: -0.0000

Data Index: 958737 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.5928. Min Act: -0.0000

Data Index: 850816 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.5700. Min Act: -0.0000

Data Index: 636453 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.5846. Min Act: -0.0000

Data Index: 1089350 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.4197. Min Act: -0.0000

Data Index: 546736 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.4899. Min Act: -0.0000

Data Index: 738443 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.4167. Min Act: -0.0000

Data Index: 894511 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1178921 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.4623. Min Act: -0.0000

Data Index: 679541 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.3339. Min Act: -0.0000

Data Index: 17762 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.3785. Min Act: -0.0000

Data Index: 54294 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.3759. Min Act: -0.0000

Data Index: 719939 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.7709. Min Range: -3.7709

Max Act: 1.3949. Min Act: -0.0000

Data Index: 862999 (C4 (Web Text))

Max Activating Token Index: 61