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

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

Neuron 1451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1695. Min Act: -0.0001

Data Index: 166129 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.3119. Min Act: -0.0001

Data Index: 383977 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2447. Min Act: -0.0001

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2830. Min Act: -0.0001

Data Index: 1084011 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2116. Min Act: -0.0001

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2940. Min Act: -0.0001

Data Index: 921006 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1215. Min Act: -0.0001

Data Index: 59273 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1605. Min Act: -0.0001

Data Index: 965702 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1895. Min Act: -0.0001

Data Index: 861087 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1428. Min Act: -0.0001

Data Index: 911204 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0217. Min Act: -0.0001

Data Index: 804442 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0141. Min Act: -0.0001

Data Index: 484590 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0483. Min Act: -0.0001

Data Index: 502588 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0108. Min Act: -0.0001

Data Index: 642682 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9790. Min Act: -0.0001

Data Index: 396442 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0561. Min Act: -0.0001

Data Index: 1031759 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1289474 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9612. Min Act: -0.0001

Data Index: 545327 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9646. Min Act: -0.0001

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9756. Min Act: -0.0001

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 836