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

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

Neuron 1133 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7927. Min Act: -0.0000

Data Index: 798181 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7364. Min Act: -0.0001

Data Index: 538369 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1175712 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6778. Min Act: -0.0001

Data Index: 725826 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7134. Min Act: -0.0001

Data Index: 169059 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6805. Min Act: -0.0000

Data Index: 377732 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6721. Min Act: -0.0000

Data Index: 822713 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6698. Min Act: -0.0000

Data Index: 371417 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6552. Min Act: -0.0000

Data Index: 417715 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5793. Min Act: -0.0000

Data Index: 836964 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1180887 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6549. Min Act: -0.0000

Data Index: 822398 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1030517 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1021072 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6111. Min Act: -0.0000

Data Index: 812097 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1358009 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1193218 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6073. Min Act: -0.0000

Data Index: 498989 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5780. Min Act: -0.0001

Data Index: 3391 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5712. Min Act: -0.0001

Data Index: 40640 (C4 (Web Text))

Max Activating Token Index: 422