Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1914 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.3013. Min Act: -0.0003

Data Index: 905097 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2336. Min Act: -0.0003

Data Index: 1065778 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2373. Min Act: -0.0003

Data Index: 299711 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.3029. Min Act: -0.0003

Data Index: 266887 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0429. Min Act: -0.0003

Data Index: 184883 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1262. Min Act: -0.0003

Data Index: 551378 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.3029. Min Range: -1.3029

Max Act: 0.9652. Min Act: -0.0003

Data Index: 434542 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0875. Min Act: -0.0003

Data Index: 1194202 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1139. Min Act: -0.0003

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0722. Min Act: -0.0004

Data Index: 372496 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1002. Min Act: -0.0003

Data Index: 450347 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0443. Min Act: -0.0003

Data Index: 1024200 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0140. Min Act: -0.0003

Data Index: 546885 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0263. Min Act: -0.0003

Data Index: 1240237 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0759. Min Act: -0.0004

Data Index: 1255209 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0254. Min Act: -0.0003

Data Index: 611156 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.3029. Min Range: -1.3029

Max Act: 0.8891. Min Act: -0.0004

Data Index: 895730 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.0358. Min Act: -0.0003

Data Index: 842302 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 1.3029. Min Range: -1.3029

Max Act: 0.9807. Min Act: -0.0003

Data Index: 684627 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.3029. Min Range: -1.3029

Max Act: 0.9996. Min Act: -0.0003

Data Index: 948259 (C4 (Web Text))

Max Activating Token Index: 831