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

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

Neuron 3454 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: 1.6612. Min Range: -1.6612

Max Act: 1.6612. Min Act: -0.0001

Data Index: 385370 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.5177. Min Act: -0.0002

Data Index: 779483 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4724. Min Act: -0.0001

Data Index: 31292 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4762. Min Act: -0.0001

Data Index: 1018183 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.5132. Min Act: -0.0001

Data Index: 1303142 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.5010. Min Act: -0.0001

Data Index: 1215823 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.5356. Min Act: -0.0001

Data Index: 6171 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4685. Min Act: -0.0001

Data Index: 1048907 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.5308. Min Act: -0.0002

Data Index: 694339 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4050. Min Act: -0.0002

Data Index: 142144 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3995. Min Act: -0.0002

Data Index: 495388 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3918. Min Act: -0.0001

Data Index: 671389 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4426. Min Act: -0.0001

Data Index: 742842 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3449. Min Act: -0.0001

Data Index: 896772 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3921. Min Act: -0.0001

Data Index: 1092239 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4297. Min Act: -0.0001

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4298. Min Act: -0.0001

Data Index: 444813 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3265. Min Act: -0.0001

Data Index: 563009 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3504. Min Act: -0.0001

Data Index: 1240832 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4461. Min Act: -0.0001

Data Index: 941782 (C4 (Web Text))

Max Activating Token Index: 628