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

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

Neuron 2754 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0001

Data Index: 551049 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0708. Min Act: -0.0002

Data Index: 84048 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1289601 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0630. Min Act: -0.0001

Data Index: 703975 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0678. Min Act: -0.0001

Data Index: 768183 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0597. Min Act: -0.0002

Data Index: 605124 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0546. Min Act: -0.0002

Data Index: 279054 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0514. Min Act: -0.0001

Data Index: 372468 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0576. Min Act: -0.0002

Data Index: 430225 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0537. Min Act: -0.0002

Data Index: 392263 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0581. Min Act: -0.0001

Data Index: 909394 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1315898 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0509. Min Act: -0.0002

Data Index: 699133 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0509. Min Act: -0.0002

Data Index: 75254 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0487. Min Act: -0.0002

Data Index: 917396 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0480. Min Act: -0.0001

Data Index: 818160 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0477. Min Act: -0.0002

Data Index: 795095 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1211427 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0473. Min Act: -0.0002

Data Index: 437191 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0421. Min Act: -0.0001

Data Index: 891057 (C4 (Web Text))

Max Activating Token Index: 810