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

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

Neuron 3447 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: 0.9435. Min Range: -0.9435

Max Act: 0.9435. Min Act: -0.0001

Data Index: 130156 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.9255. Min Act: -0.0001

Data Index: 638161 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.8700. Min Act: -0.0001

Data Index: 357067 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.8331. Min Act: -0.0001

Data Index: 834821 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7915. Min Act: -0.0001

Data Index: 491023 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.8129. Min Act: -0.0001

Data Index: 934593 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7940. Min Act: -0.0001

Data Index: 529279 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7991. Min Act: -0.0001

Data Index: 414326 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1068701 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7602. Min Act: -0.0001

Data Index: 231650 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7607. Min Act: -0.0001

Data Index: 872718 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7894. Min Act: -0.0001

Data Index: 155702 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.8141. Min Act: -0.0001

Data Index: 669185 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7822. Min Act: -0.0001

Data Index: 939311 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7589. Min Act: -0.0001

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1288504 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7721. Min Act: -0.0001

Data Index: 817458 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7967. Min Act: -0.0001

Data Index: 1201727 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7574. Min Act: -0.0001

Data Index: 1270997 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7951. Min Act: -0.0001

Data Index: 546650 (C4 (Web Text))

Max Activating Token Index: 137