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

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

Neuron 2125 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.5382. Min Act: -0.0001

Data Index: 998883 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.5635. Min Act: -0.0001

Data Index: 237686 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3843. Min Act: -0.0001

Data Index: 713688 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3051. Min Act: -0.0001

Data Index: 602098 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3546. Min Act: -0.0001

Data Index: 61681 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2640. Min Act: -0.0001

Data Index: 1252169 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3275. Min Act: -0.0001

Data Index: 1006823 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.3583. Min Act: -0.0001

Data Index: 325910 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2771. Min Act: -0.0001

Data Index: 396813 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2645. Min Act: -0.0001

Data Index: 1043156 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2433. Min Act: -0.0001

Data Index: 226579 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2524. Min Act: -0.0001

Data Index: 935995 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2007. Min Act: -0.0001

Data Index: 924807 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.1629. Min Act: -0.0001

Data Index: 502862 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2358. Min Act: -0.0001

Data Index: 268829 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2505. Min Act: -0.0001

Data Index: 1239827 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1271661 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.2141. Min Act: -0.0001

Data Index: 470980 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.1639. Min Act: -0.0001

Data Index: 272844 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.5635. Min Range: -1.5635

Max Act: 1.1921. Min Act: -0.0001

Data Index: 744258 (C4 (Web Text))

Max Activating Token Index: 177