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

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

Neuron 1430 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: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1334783 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0997. Min Act: -0.0001

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0853. Min Act: -0.0001

Data Index: 968961 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0761. Min Act: -0.0001

Data Index: 809120 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0896. Min Act: -0.0001

Data Index: 35487 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0872. Min Act: -0.0001

Data Index: 184053 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1047849 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0814. Min Act: -0.0001

Data Index: 528069 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0863. Min Act: -0.0001

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0715. Min Act: -0.0001

Data Index: 436562 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0814. Min Act: -0.0001

Data Index: 328700 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0764. Min Act: -0.0001

Data Index: 613520 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0801. Min Act: -0.0001

Data Index: 621488 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0777. Min Act: -0.0001

Data Index: 130526 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1136346 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0737. Min Act: -0.0001

Data Index: 321828 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1026228 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1255027 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1190516 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1052660 (C4 (Web Text))

Max Activating Token Index: 966