Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5333 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6420. Min Range: -6.6420

Max Act: 6.0970. Min Act: -0.0000

Data Index: 774699 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 6.6420. Min Range: -6.6420

Max Act: 6.6420. Min Act: -0.0000

Data Index: 998961 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 6.6420. Min Range: -6.6420

Max Act: 4.8560. Min Act: 0.0000

Data Index: 1309963 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 6.6420. Min Range: -6.6420

Max Act: 5.4068. Min Act: -0.0000

Data Index: 684134 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 6.6420. Min Range: -6.6420

Max Act: 4.9074. Min Act: -0.0000

Data Index: 655265 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.8112. Min Act: -0.0000

Data Index: 923065 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.6535. Min Act: 0.0000

Data Index: 1128459 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.9290. Min Act: -0.0000

Data Index: 272758 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.1717. Min Act: -0.0000

Data Index: 564782 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.5360. Min Act: 0.0000

Data Index: 634774 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.7792. Min Act: 0.0001

Data Index: 736201 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.7236. Min Act: 0.0000

Data Index: 325050 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.9768. Min Act: 0.0000

Data Index: 443824 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 6.6420. Min Range: -6.6420

Max Act: 3.0770. Min Act: 0.0000

Data Index: 954857 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.7254. Min Act: -0.0000

Data Index: 165727 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.8008. Min Act: -0.0000

Data Index: 1010987 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.6773. Min Act: 0.0000

Data Index: 1074608 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.9883. Min Act: 0.0001

Data Index: 169849 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.1947. Min Act: -0.0000

Data Index: 219217 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 6.6420. Min Range: -6.6420

Max Act: 2.9887. Min Act: -0.0000

Data Index: 130116 (C4 (Web Text))

Max Activating Token Index: 343