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

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

Neuron 558 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.7841. Min Act: -0.0001

Data Index: 873786 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.6942. Min Act: -0.0001

Data Index: 1018046 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.4175. Min Act: -0.0001

Data Index: 1017565 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.4089. Min Act: -0.0001

Data Index: 1272084 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.4453. Min Act: -0.0001

Data Index: 305116 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.3858. Min Act: -0.0001

Data Index: 404496 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2936. Min Act: -0.0001

Data Index: 1098055 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.4062. Min Act: -0.0001

Data Index: 852066 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.3135. Min Act: -0.0001

Data Index: 337700 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2705. Min Act: -0.0001

Data Index: 275079 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2589. Min Act: -0.0001

Data Index: 1074208 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2796. Min Act: -0.0001

Data Index: 741722 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2845. Min Act: -0.0001

Data Index: 258875 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2065. Min Act: -0.0001

Data Index: 531518 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2804. Min Act: -0.0001

Data Index: 317560 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2121. Min Act: -0.0001

Data Index: 356099 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2149. Min Act: -0.0001

Data Index: 1164509 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2089. Min Act: -0.0001

Data Index: 511185 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.1610. Min Act: -0.0001

Data Index: 1282323 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.7841. Min Range: -1.7841

Max Act: 1.2080. Min Act: -0.0001

Data Index: 925552 (C4 (Web Text))

Max Activating Token Index: 791