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

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

Neuron 1168 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1684. Min Act: -0.0001

Data Index: 533016 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1247949 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1136. Min Act: -0.0001

Data Index: 988713 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0730. Min Act: -0.0001

Data Index: 884440 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0994. Min Act: -0.0000

Data Index: 608766 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1012. Min Act: -0.0000

Data Index: 534455 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0423. Min Act: -0.0001

Data Index: 156202 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0430. Min Act: -0.0001

Data Index: 790513 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9803. Min Act: -0.0001

Data Index: 1515007 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1373. Min Act: -0.0000

Data Index: 24599 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0370. Min Act: -0.0000

Data Index: 994190 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0311. Min Act: -0.0001

Data Index: 770195 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.0232. Min Act: -0.0000

Data Index: 801797 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8678. Min Act: -0.0001

Data Index: 220523 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1265887 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9842. Min Act: -0.0001

Data Index: 787020 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9198. Min Act: -0.0000

Data Index: 682105 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1228819 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8854. Min Act: -0.0001

Data Index: 908451 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8832. Min Act: -0.0000

Data Index: 595546 (C4 (Web Text))

Max Activating Token Index: 137