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

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

Neuron 1109 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: 3.7279. Min Range: -3.7279

Max Act: 3.7279. Min Act: -0.0002

Data Index: 545742 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.3874. Min Act: -0.0002

Data Index: 808520 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.3272. Min Act: -0.0002

Data Index: 850110 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.2304. Min Act: -0.0003

Data Index: 169120 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.2193. Min Act: -0.0002

Data Index: 191414 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0680. Min Act: -0.0002

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0827. Min Act: -0.0002

Data Index: 794985 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0969. Min Act: -0.0002

Data Index: 1152512 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9938. Min Act: -0.0002

Data Index: 436310 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0658. Min Act: -0.0002

Data Index: 1312974 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9759. Min Act: -0.0002

Data Index: 1023251 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0156. Min Act: -0.0002

Data Index: 1227653 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0483. Min Act: -0.0002

Data Index: 1271857 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9331. Min Act: -0.0002

Data Index: 414526 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 3.7279. Min Range: -3.7279

Max Act: 3.0154. Min Act: -0.0002

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9339. Min Act: -0.0002

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9768. Min Act: -0.0002

Data Index: 402242 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9581. Min Act: -0.0002

Data Index: 719809 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.9017. Min Act: -0.0003

Data Index: 586670 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 3.7279. Min Range: -3.7279

Max Act: 2.8955. Min Act: -0.0002

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 272