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

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

Neuron 1670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2448. Min Act: -0.0001

Data Index: 822704 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.4625. Min Act: -0.0001

Data Index: 269134 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.1557. Min Act: -0.0001

Data Index: 301294 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0049. Min Act: -0.0001

Data Index: 551330 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0753. Min Act: -0.0001

Data Index: 202503 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0630. Min Act: -0.0001

Data Index: 818142 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.1344. Min Act: -0.0001

Data Index: 931017 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.1020. Min Act: -0.0001

Data Index: 930308 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0530. Min Act: -0.0001

Data Index: 463321 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0554. Min Act: -0.0001

Data Index: 246721 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0769. Min Act: -0.0001

Data Index: 1013224 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0336. Min Act: -0.0001

Data Index: 774621 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.4625. Min Range: -1.4625

Max Act: 0.9481. Min Act: -0.0001

Data Index: 808958 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0342. Min Act: -0.0001

Data Index: 1268484 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0263. Min Act: -0.0001

Data Index: 1001319 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0219. Min Act: -0.0001

Data Index: 323147 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.4625. Min Range: -1.4625

Max Act: 0.9675. Min Act: -0.0001

Data Index: 259332 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0183. Min Act: -0.0001

Data Index: 1306719 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0109. Min Act: -0.0001

Data Index: 973818 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0012. Min Act: -0.0001

Data Index: 1339897 (C4 (Web Text))

Max Activating Token Index: 564