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

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

Neuron 4948 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: 1.7521. Min Range: -1.7521

Max Act: 1.7521. Min Act: -0.0002

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6878. Min Act: -0.0002

Data Index: 623248 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6498. Min Act: -0.0002

Data Index: 1029266 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6327. Min Act: -0.0002

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6092. Min Act: -0.0002

Data Index: 939539 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6378. Min Act: -0.0002

Data Index: 227994 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.6276. Min Act: -0.0002

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5916. Min Act: -0.0002

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5740. Min Act: -0.0002

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5172. Min Act: -0.0002

Data Index: 139347 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5606. Min Act: -0.0002

Data Index: 498862 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5974. Min Act: -0.0002

Data Index: 379522 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5427. Min Act: -0.0002

Data Index: 676849 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.4914. Min Act: -0.0002

Data Index: 59575 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5793. Min Act: -0.0002

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5376. Min Act: -0.0003

Data Index: 1326907 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5119. Min Act: -0.0002

Data Index: 555794 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.4750. Min Act: -0.0002

Data Index: 1341690 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5486. Min Act: -0.0002

Data Index: 970114 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.7521. Min Range: -1.7521

Max Act: 1.5386. Min Act: -0.0002

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 927