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

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

Neuron 75 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1151520 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0827. Min Act: -0.0001

Data Index: 119265 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0863. Min Act: -0.0001

Data Index: 921270 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0756. Min Act: -0.0001

Data Index: 983340 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0738. Min Act: -0.0001

Data Index: 846257 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0666. Min Act: -0.0001

Data Index: 828393 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0684. Min Act: -0.0001

Data Index: 891386 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0661. Min Act: -0.0001

Data Index: 508453 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1140052 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0653. Min Act: -0.0001

Data Index: 343793 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0624. Min Act: -0.0001

Data Index: 252090 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0669. Min Act: -0.0001

Data Index: 194872 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1131156 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1196795 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0644. Min Act: -0.0001

Data Index: 841877 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1289727 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1207483 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1285907 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0665. Min Act: -0.0001

Data Index: 83659 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0638. Min Act: -0.0001

Data Index: 937028 (C4 (Web Text))

Max Activating Token Index: 350