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

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

Neuron 5090 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: 0.0774. Min Range: -0.0774

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1298166 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0002

Data Index: 367225 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0724. Min Act: -0.0002

Data Index: 96235 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0704. Min Act: -0.0002

Data Index: 770901 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1236890 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0631. Min Act: -0.0002

Data Index: 292937 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1276052 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0612. Min Act: -0.0002

Data Index: 575876 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1248081 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0536. Min Act: -0.0002

Data Index: 98970 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0536. Min Act: -0.0003

Data Index: 634219 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1036556 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0532. Min Act: -0.0002

Data Index: 553325 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0523. Min Act: -0.0003

Data Index: 448532 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0517. Min Act: -0.0002

Data Index: 907319 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1269768 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0509. Min Act: -0.0002

Data Index: 300278 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0496. Min Act: -0.0002

Data Index: 69592 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0487. Min Act: -0.0002

Data Index: 947629 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0478. Min Act: -0.0002

Data Index: 965014 (C4 (Web Text))

Max Activating Token Index: 53