Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1183 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1119072 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5481. Min Act: -0.0000

Data Index: 957891 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1045073 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5547. Min Act: -0.0000

Data Index: 296437 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5357. Min Act: -0.0000

Data Index: 513374 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.5267. Min Act: -0.0000

Data Index: 378740 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4863. Min Act: -0.0000

Data Index: 493530 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4986. Min Act: -0.0000

Data Index: 944082 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4792. Min Act: -0.0000

Data Index: 701447 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4648. Min Act: -0.0000

Data Index: 583535 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1025690 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4244. Min Act: -0.0000

Data Index: 710576 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4623. Min Act: -0.0000

Data Index: 343837 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1154526 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4243. Min Act: -0.0000

Data Index: 750869 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1187144 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4302. Min Act: -0.0000

Data Index: 285876 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4456. Min Act: -0.0000

Data Index: 166014 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4445. Min Act: -0.0000

Data Index: 705061 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.5742. Min Range: -0.5742

Max Act: 0.4421. Min Act: -0.0000

Data Index: 382019 (C4 (Web Text))

Max Activating Token Index: 668