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

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

Neuron 2043 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6019. Min Range: -1.6019

Max Act: 1.6019. Min Act: -0.0002

Data Index: 1241904 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.6019. Min Range: -1.6019

Max Act: 1.4659. Min Act: -0.0002

Data Index: 1271294 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.6019. Min Range: -1.6019

Max Act: 1.2157. Min Act: -0.0003

Data Index: 1247123 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.6019. Min Range: -1.6019

Max Act: 1.0328. Min Act: -0.0003

Data Index: 693103 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.9756. Min Act: -0.0002

Data Index: 591868 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8917. Min Act: -0.0003

Data Index: 1342766 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8549. Min Act: -0.0003

Data Index: 298409 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.9113. Min Act: -0.0003

Data Index: 1064563 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8715. Min Act: -0.0003

Data Index: 578278 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8739. Min Act: -0.0003

Data Index: 1176258 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8823. Min Act: -0.0003

Data Index: 568734 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8658. Min Act: -0.0003

Data Index: 994695 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8366. Min Act: -0.0003

Data Index: 589214 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8646. Min Act: -0.0003

Data Index: 1180896 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8388. Min Act: -0.0003

Data Index: 811186 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8315. Min Act: -0.0003

Data Index: 1259619 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.7919. Min Act: -0.0002

Data Index: 773434 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8386. Min Act: -0.0003

Data Index: 676935 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.7841. Min Act: -0.0003

Data Index: 759512 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.6019. Min Range: -1.6019

Max Act: 0.8044. Min Act: -0.0003

Data Index: 1268546 (C4 (Web Text))

Max Activating Token Index: 522