Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.4017. Min Act: -0.0000

Data Index: 1057942 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.2285. Min Act: -0.0000

Data Index: 773467 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.1132. Min Act: -0.0000

Data Index: 72728 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.7038. Min Act: -0.0000

Data Index: 109098 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.5295. Min Act: -0.0000

Data Index: 362187 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.5069. Min Act: -0.0000

Data Index: 764673 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.4875. Min Act: -0.0000

Data Index: 971568 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.4608. Min Act: -0.0000

Data Index: 1020098 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.3881. Min Act: -0.0000

Data Index: 1353828 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.2446. Min Act: -0.0000

Data Index: 1070646 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.2263. Min Act: -0.0000

Data Index: 587733 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.3664. Min Act: -0.0000

Data Index: 216662 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.5308. Min Act: -0.0000

Data Index: 574246 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.2759. Min Act: -0.0000

Data Index: 510251 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.2627. Min Act: -0.0000

Data Index: 362202 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.2244. Min Act: -0.0000

Data Index: 272459 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.1757. Min Act: -0.0000

Data Index: 103857 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.1025. Min Act: -0.0000

Data Index: 413447 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.1512. Min Act: -0.0000

Data Index: 1349322 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.1420. Min Act: -0.0000

Data Index: 1147253 (C4 (Web Text))

Max Activating Token Index: 667