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

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

Neuron 5070 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: 0.1344. Min Range: -0.1344

Max Act: 0.1344. Min Act: -0.0003

Data Index: 1197820 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1092. Min Act: -0.0002

Data Index: 540576 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1143872 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0919. Min Act: -0.0002

Data Index: 199417 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0886. Min Act: -0.0002

Data Index: 767703 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0869. Min Act: -0.0002

Data Index: 284762 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0858. Min Act: -0.0002

Data Index: 936430 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0838. Min Act: -0.0002

Data Index: 857211 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1135737 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0806. Min Act: -0.0002

Data Index: 586384 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0799. Min Act: -0.0003

Data Index: 340725 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0754. Min Act: -0.0002

Data Index: 501661 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1329073 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0703. Min Act: -0.0002

Data Index: 626470 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0665. Min Act: -0.0002

Data Index: 720301 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0668. Min Act: -0.0002

Data Index: 288681 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0670. Min Act: -0.0002

Data Index: 906977 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0665. Min Act: -0.0002

Data Index: 381595 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0675. Min Act: -0.0002

Data Index: 965796 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0656. Min Act: -0.0002

Data Index: 75021 (C4 (Web Text))

Max Activating Token Index: 784