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

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

Neuron 366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0001

Data Index: 1156445 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1117866 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1249. Min Act: -0.0001

Data Index: 542179 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1271911 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0904. Min Act: -0.0001

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1165. Min Act: -0.0001

Data Index: 628142 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1082. Min Act: -0.0001

Data Index: 574185 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0075. Min Act: -0.0001

Data Index: 1251686 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0025. Min Act: -0.0001

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0346. Min Act: -0.0001

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0414. Min Act: -0.0001

Data Index: 824104 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0432. Min Act: -0.0001

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0118. Min Act: -0.0001

Data Index: 1357569 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9807. Min Act: -0.0001

Data Index: 507130 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0302. Min Act: -0.0001

Data Index: 60673 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0254. Min Act: -0.0001

Data Index: 8717 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0436. Min Act: -0.0001

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9756. Min Act: -0.0001

Data Index: 1211544 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9482. Min Act: -0.0001

Data Index: 112220 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9988. Min Act: -0.0001

Data Index: 584150 (C4 (Web Text))

Max Activating Token Index: 911