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

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

Neuron 3246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 622522 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5252. Min Act: -0.0001

Data Index: 963785 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4916. Min Act: -0.0001

Data Index: 286605 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4941. Min Act: -0.0001

Data Index: 918731 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4831. Min Act: -0.0000

Data Index: 394962 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1186907 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1318077 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4402. Min Act: -0.0001

Data Index: 544478 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4351. Min Act: -0.0001

Data Index: 1195093 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4220. Min Act: -0.0001

Data Index: 1121260 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4246. Min Act: -0.0001

Data Index: 342704 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3650. Min Act: -0.0001

Data Index: 773318 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3582. Min Act: -0.0001

Data Index: 681307 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3775. Min Act: -0.0001

Data Index: 23942 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4152. Min Act: -0.0001

Data Index: 23587 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4063. Min Act: -0.0001

Data Index: 257544 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4155. Min Act: -0.0001

Data Index: 98110 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3601. Min Act: -0.0001

Data Index: 874589 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3849. Min Act: -0.0001

Data Index: 1001288 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1281702 (C4 (Web Text))

Max Activating Token Index: 153