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

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

Neuron 26 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8868. Min Act: -0.0000

Data Index: 275038 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1012472 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.9235. Min Act: -0.0000

Data Index: 324302 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8711. Min Act: -0.0000

Data Index: 509384 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8841. Min Act: -0.0000

Data Index: 883085 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8698. Min Act: -0.0000

Data Index: 792895 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8559. Min Act: -0.0000

Data Index: 849834 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8405. Min Act: -0.0000

Data Index: 80103 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8025. Min Act: -0.0000

Data Index: 100501 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8308. Min Act: -0.0000

Data Index: 420502 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8190. Min Act: -0.0000

Data Index: 716759 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7969. Min Act: -0.0000

Data Index: 683317 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1327530 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1070621 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1098989 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7182. Min Act: -0.0000

Data Index: 727602 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7783. Min Act: -0.0000

Data Index: 270945 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1334858 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7076. Min Act: -0.0000

Data Index: 311486 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6949. Min Act: -0.0000

Data Index: 609045 (C4 (Web Text))

Max Activating Token Index: 397