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

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

Neuron 2486 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7369. Min Act: -0.0002

Data Index: 807091 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7119. Min Act: -0.0002

Data Index: 1022708 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6935. Min Act: -0.0002

Data Index: 306491 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6912. Min Act: -0.0002

Data Index: 939875 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6893. Min Act: -0.0002

Data Index: 336759 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6882. Min Act: -0.0002

Data Index: 424975 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6462. Min Act: -0.0002

Data Index: 207356 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6480. Min Act: -0.0002

Data Index: 1565095 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6382. Min Act: -0.0002

Data Index: 605341 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6378. Min Act: -0.0002

Data Index: 1302275 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6283. Min Act: -0.0002

Data Index: 420721 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6384. Min Act: -0.0002

Data Index: 438898 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6248. Min Act: -0.0002

Data Index: 772315 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6356. Min Act: -0.0002

Data Index: 241981 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6243. Min Act: -0.0002

Data Index: 977819 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6188. Min Act: -0.0002

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6211. Min Act: -0.0002

Data Index: 162464 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6150. Min Act: -0.0002

Data Index: 817839 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6091. Min Act: -0.0002

Data Index: 578510 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6137. Min Act: -0.0002

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 95