Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1195 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7621. Min Act: -0.0003

Data Index: 1171806 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6740. Min Act: -0.0003

Data Index: 304558 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6646. Min Act: -0.0003

Data Index: 1257698 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6824. Min Act: -0.0003

Data Index: 1010869 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6501. Min Act: -0.0003

Data Index: 1280142 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6307. Min Act: -0.0003

Data Index: 1354439 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6474. Min Act: -0.0003

Data Index: 45071 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6266. Min Act: -0.0002

Data Index: 945636 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6373. Min Act: -0.0003

Data Index: 305521 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6037. Min Act: -0.0003

Data Index: 761972 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6046. Min Act: -0.0003

Data Index: 1273552 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6086. Min Act: -0.0003

Data Index: 1345862 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6006. Min Act: -0.0003

Data Index: 1016006 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6122. Min Act: -0.0003

Data Index: 1223213 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5884. Min Act: -0.0003

Data Index: 997508 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5872. Min Act: -0.0003

Data Index: 955917 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5982. Min Act: -0.0003

Data Index: 1084900 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5947. Min Act: -0.0003

Data Index: 471214 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5771. Min Act: -0.0003

Data Index: 544602 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5832. Min Act: -0.0003

Data Index: 914657 (C4 (Web Text))

Max Activating Token Index: 248