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

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

Neuron 2122 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.2296. Min Act: -0.0000

Data Index: 414922 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.1155. Min Act: -0.0000

Data Index: 280957 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0209. Min Act: -0.0000

Data Index: 679421 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0304. Min Act: -0.0000

Data Index: 346764 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9672. Min Act: -0.0000

Data Index: 571297 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0218. Min Act: -0.0000

Data Index: 800524 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9342. Min Act: -0.0000

Data Index: 518141 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9819. Min Act: 0.0000

Data Index: 431553 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9112. Min Act: -0.0000

Data Index: 696736 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8906. Min Act: -0.0000

Data Index: 618465 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8907. Min Act: -0.0000

Data Index: 425104 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8815. Min Act: -0.0000

Data Index: 599711 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1168601 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1265073 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8587. Min Act: -0.0000

Data Index: 948117 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8288. Min Act: -0.0000

Data Index: 709497 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.7799. Min Act: -0.0000

Data Index: 904048 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1127733 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1282500 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1264445 (C4 (Web Text))

Max Activating Token Index: 203