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

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

Neuron 3855 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0231. Min Range: -4.0231

Max Act: 4.0231. Min Act: -0.0000

Data Index: 1078862 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 4.0231. Min Range: -4.0231

Max Act: 3.3127. Min Act: -0.0000

Data Index: 440796 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 4.0231. Min Range: -4.0231

Max Act: 3.0360. Min Act: -0.0000

Data Index: 302198 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.7308. Min Act: -0.0000

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.5504. Min Act: -0.0000

Data Index: 33927 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.2542. Min Act: -0.0000

Data Index: 594715 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.1327. Min Act: -0.0000

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.2378. Min Act: -0.0000

Data Index: 735891 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.2827. Min Act: -0.0000

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.1189. Min Act: -0.0000

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8243. Min Act: -0.0000

Data Index: 782205 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.9206. Min Act: -0.0000

Data Index: 798139 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8186. Min Act: -0.0000

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1288137 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.7347. Min Act: -0.0000

Data Index: 752338 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 4.0231. Min Range: -4.0231

Max Act: 2.0061. Min Act: -0.0000

Data Index: 190283 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.9659. Min Act: -0.0000

Data Index: 958038 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8154. Min Act: -0.0000

Data Index: 72038 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8134. Min Act: -0.0000

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 4.0231. Min Range: -4.0231

Max Act: 1.8086. Min Act: -0.0000

Data Index: 365772 (C4 (Web Text))

Max Activating Token Index: 770