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

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

Neuron 2478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5560. Min Range: -1.5560

Max Act: 1.5560. Min Act: -0.0000

Data Index: 267312 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.9491. Min Act: -0.0000

Data Index: 607944 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.9914. Min Act: -0.0000

Data Index: 369510 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1039239 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.8410. Min Act: -0.0000

Data Index: 349063 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.8362. Min Act: -0.0000

Data Index: 197785 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.9142. Min Act: -0.0000

Data Index: 331833 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.8685. Min Act: -0.0000

Data Index: 906839 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7921. Min Act: -0.0000

Data Index: 393395 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7942. Min Act: -0.0000

Data Index: 758607 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7914. Min Act: -0.0000

Data Index: 312517 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.8101. Min Act: -0.0000

Data Index: 653222 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7867. Min Act: -0.0000

Data Index: 166548 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7537. Min Act: -0.0000

Data Index: 28452 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1272466 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.8275. Min Act: -0.0000

Data Index: 504966 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7148. Min Act: -0.0000

Data Index: 476690 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7260. Min Act: -0.0000

Data Index: 570764 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.7256. Min Act: -0.0000

Data Index: 789881 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.5560. Min Range: -1.5560

Max Act: 0.6539. Min Act: -0.0000

Data Index: 963783 (C4 (Web Text))

Max Activating Token Index: 791