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

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

Neuron 703 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1177. Min Act: -0.0000

Data Index: 450294 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0000

Data Index: 968878 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1194. Min Act: -0.0000

Data Index: 96627 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1124. Min Act: -0.0000

Data Index: 387727 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1100. Min Act: -0.0000

Data Index: 438055 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1095. Min Act: -0.0000

Data Index: 249595 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1476819 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1259. Min Act: -0.0000

Data Index: 894926 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1001110 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1514550 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1152955 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0834. Min Act: -0.0000

Data Index: 185041 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1487596 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1026261 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0937. Min Act: -0.0000

Data Index: 452997 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0878. Min Act: -0.0000

Data Index: 677983 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1608128 (Python Code)

Max Activating Token Index: 731

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0934. Min Act: -0.0000

Data Index: 676990 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1634030 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1504628 (Python Code)

Max Activating Token Index: 790