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

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

Neuron 3864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8841. Min Range: -8.8841

Max Act: 8.8841. Min Act: -0.0001

Data Index: 369223 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 8.8841. Min Range: -8.8841

Max Act: 8.0411. Min Act: -0.0000

Data Index: 504826 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.4100. Min Act: -0.0001

Data Index: 765056 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.5858. Min Act: -0.0001

Data Index: 445462 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.7203. Min Act: -0.0001

Data Index: 26336 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.7299. Min Act: -0.0001

Data Index: 255534 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.3301. Min Act: -0.0000

Data Index: 1329569 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.4373. Min Act: -0.0001

Data Index: 551007 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.7744. Min Act: -0.0001

Data Index: 84471 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.2467. Min Act: -0.0001

Data Index: 599663 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.0698. Min Act: -0.0001

Data Index: 970749 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.9218. Min Act: -0.0000

Data Index: 86896 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.9263. Min Act: -0.0001

Data Index: 391694 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.5234. Min Act: -0.0000

Data Index: 962003 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.9187. Min Act: -0.0001

Data Index: 686550 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 8.8841. Min Range: -8.8841

Max Act: 7.0307. Min Act: -0.0001

Data Index: 149055 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.1643. Min Act: -0.0001

Data Index: 995069 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.5990. Min Act: -0.0000

Data Index: 989371 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.6256. Min Act: -0.0001

Data Index: 797823 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 8.8841. Min Range: -8.8841

Max Act: 6.6731. Min Act: -0.0001

Data Index: 326619 (C4 (Web Text))

Max Activating Token Index: 907