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

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

Neuron 2397 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9507. Min Act: -0.0000

Data Index: 231179 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9088. Min Act: -0.0000

Data Index: 656267 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8566. Min Act: -0.0000

Data Index: 790527 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1196590 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8336. Min Act: -0.0000

Data Index: 640186 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7668. Min Act: -0.0000

Data Index: 683361 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7005. Min Act: -0.0000

Data Index: 843028 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7015. Min Act: -0.0000

Data Index: 165636 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1470088 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1074042 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1038583 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1144631 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.5144. Min Act: -0.0000

Data Index: 393554 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1258550 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6627. Min Act: -0.0000

Data Index: 129905 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6808. Min Act: -0.0000

Data Index: 421831 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6650. Min Act: -0.0000

Data Index: 188608 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6459. Min Act: -0.0000

Data Index: 689401 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1349738 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.5804. Min Act: -0.0000

Data Index: 38624 (C4 (Web Text))

Max Activating Token Index: 633