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

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

Neuron 4586 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: 0.1753. Min Range: -0.1753

Max Act: 0.1753. Min Act: -0.0000

Data Index: 434814 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1165. Min Act: -0.0000

Data Index: 788502 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1167. Min Act: -0.0000

Data Index: 129443 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1154017 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1143. Min Act: -0.0000

Data Index: 167730 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1138. Min Act: -0.0000

Data Index: 386633 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1173. Min Act: -0.0000

Data Index: 789219 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1039. Min Act: -0.0000

Data Index: 227823 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1123. Min Act: -0.0000

Data Index: 205563 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1147137 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1068. Min Act: -0.0000

Data Index: 545023 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1168111 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1060. Min Act: -0.0000

Data Index: 757593 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0956. Min Act: -0.0000

Data Index: 213849 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0982. Min Act: -0.0000

Data Index: 603846 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1074942 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0962. Min Act: -0.0000

Data Index: 568628 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0896. Min Act: -0.0000

Data Index: 722027 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0915. Min Act: -0.0000

Data Index: 591308 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1068223 (C4 (Web Text))

Max Activating Token Index: 668