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

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

Neuron 3448 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1310. Min Act: -0.0002

Data Index: 794766 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1349. Min Act: -0.0002

Data Index: 426486 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1167856 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1222. Min Act: -0.0002

Data Index: 631553 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1166. Min Act: -0.0001

Data Index: 788112 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1115. Min Act: -0.0001

Data Index: 542987 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1249336 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1123. Min Act: -0.0001

Data Index: 934847 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1092. Min Act: -0.0001

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1080. Min Act: -0.0002

Data Index: 779506 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1146. Min Act: -0.0002

Data Index: 837484 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1094. Min Act: -0.0001

Data Index: 242061 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1057. Min Act: -0.0001

Data Index: 339588 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.0976. Min Act: -0.0002

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1034. Min Act: -0.0002

Data Index: 375450 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1031. Min Act: -0.0002

Data Index: 756238 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.0986. Min Act: -0.0002

Data Index: 324543 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.0989. Min Act: -0.0001

Data Index: 362353 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.0992. Min Act: -0.0001

Data Index: 270612 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1001. Min Act: -0.0001

Data Index: 106526 (C4 (Web Text))

Max Activating Token Index: 866