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

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

Neuron 3959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.0432. Min Act: -0.0000

Data Index: 883774 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.1374. Min Act: -0.0000

Data Index: 2642 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 2.1950. Min Range: -2.1950

Max Act: 2.1950. Min Act: -0.0000

Data Index: 1208019 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.8018. Min Act: -0.0000

Data Index: 239787 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.7766. Min Act: -0.0000

Data Index: 783784 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.8586. Min Act: -0.0000

Data Index: 917382 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.7351. Min Act: -0.0000

Data Index: 340522 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6292. Min Act: -0.0000

Data Index: 731166 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6546. Min Act: -0.0000

Data Index: 505137 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6545. Min Act: -0.0000

Data Index: 1295129 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.4227. Min Act: -0.0000

Data Index: 768478 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.7274. Min Act: -0.0000

Data Index: 403077 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6144. Min Act: -0.0000

Data Index: 884063 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6762. Min Act: -0.0000

Data Index: 125650 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6172. Min Act: -0.0000

Data Index: 459750 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.4214. Min Act: -0.0000

Data Index: 325122 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.5348. Min Act: -0.0000

Data Index: 512367 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.5809. Min Act: -0.0000

Data Index: 955139 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6814. Min Act: -0.0000

Data Index: 31583 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 2.1950. Min Range: -2.1950

Max Act: 1.6768. Min Act: -0.0000

Data Index: 1055505 (C4 (Web Text))

Max Activating Token Index: 607