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

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

Neuron 1198 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: 3.2390. Min Range: -3.2390

Max Act: 3.2390. Min Act: -0.0000

Data Index: 1278551 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6087. Min Act: -0.0000

Data Index: 1277646 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.5086. Min Act: -0.0000

Data Index: 674790 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1269737 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.5815. Min Act: -0.0000

Data Index: 692956 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6972. Min Act: -0.0001

Data Index: 394989 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1333387 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.8866. Min Act: -0.0001

Data Index: 1142183 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.8179. Min Act: -0.0000

Data Index: 1120947 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.9909. Min Act: -0.0000

Data Index: 1172020 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.9520. Min Act: -0.0000

Data Index: 24274 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.6373. Min Act: -0.0001

Data Index: 225772 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.8171. Min Act: -0.0000

Data Index: 705781 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.6896. Min Act: -0.0000

Data Index: 438090 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.6458. Min Act: -0.0000

Data Index: 535217 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.7298. Min Act: -0.0000

Data Index: 826617 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.6009. Min Act: -0.0000

Data Index: 320731 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.7608. Min Act: -0.0000

Data Index: 159350 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.5271. Min Act: -0.0000

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.5606. Min Act: -0.0000

Data Index: 294088 (C4 (Web Text))

Max Activating Token Index: 403