Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4055. Min Act: -0.0001

Data Index: 472724 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4001. Min Act: -0.0001

Data Index: 538986 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1096260 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3935. Min Act: -0.0001

Data Index: 711237 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3870. Min Act: -0.0001

Data Index: 571178 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3673. Min Act: -0.0001

Data Index: 625766 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1044945 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1237470 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1022480 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3635. Min Act: -0.0001

Data Index: 135715 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1299166 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3466. Min Act: -0.0001

Data Index: 705185 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3845. Min Act: -0.0001

Data Index: 667791 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3715. Min Act: -0.0001

Data Index: 394187 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1215635 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3709. Min Act: -0.0001

Data Index: 67944 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4028. Min Act: -0.0001

Data Index: 483064 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3805. Min Act: -0.0001

Data Index: 1214304 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1099719 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3675. Min Act: -0.0001

Data Index: 1212553 (C4 (Web Text))

Max Activating Token Index: 1008