Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 955 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.2426. Min Act: -0.0005

Data Index: 392837 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1391. Min Act: -0.0005

Data Index: 1031358 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1599. Min Act: -0.0005

Data Index: 839777 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1505. Min Act: -0.0005

Data Index: 1087102 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1093. Min Act: -0.0005

Data Index: 1047894 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0538. Min Act: -0.0005

Data Index: 468873 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0458. Min Act: -0.0005

Data Index: 619991 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.1224. Min Act: -0.0005

Data Index: 780266 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0497. Min Act: -0.0005

Data Index: 913711 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0413. Min Act: -0.0005

Data Index: 555594 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0275. Min Act: -0.0005

Data Index: 1217440 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9561. Min Act: -0.0005

Data Index: 533976 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0112. Min Act: -0.0005

Data Index: 852680 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0145. Min Act: -0.0005

Data Index: 404894 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.2426. Min Range: -1.2426

Max Act: 1.0057. Min Act: -0.0005

Data Index: 838839 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9848. Min Act: -0.0005

Data Index: 1254242 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9788. Min Act: -0.0005

Data Index: 1177610 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9439. Min Act: -0.0005

Data Index: 956582 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9948. Min Act: -0.0005

Data Index: 58887 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.2426. Min Range: -1.2426

Max Act: 0.9678. Min Act: -0.0004

Data Index: 1035058 (C4 (Web Text))

Max Activating Token Index: 235