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

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

Neuron 1426 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: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0002

Data Index: 18403 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1383. Min Act: -0.0002

Data Index: 144849 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1242. Min Act: -0.0002

Data Index: 386707 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1182. Min Act: -0.0002

Data Index: 925946 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1147. Min Act: -0.0002

Data Index: 655882 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1158930 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1119. Min Act: -0.0002

Data Index: 537677 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1106. Min Act: -0.0002

Data Index: 526488 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1106. Min Act: -0.0003

Data Index: 72458 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1111. Min Act: -0.0002

Data Index: 382259 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1087. Min Act: -0.0003

Data Index: 973540 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1072. Min Act: -0.0002

Data Index: 590861 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1040. Min Act: -0.0002

Data Index: 628796 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1021. Min Act: -0.0002

Data Index: 218595 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1054. Min Act: -0.0002

Data Index: 473654 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1100990 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1011475 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1048. Min Act: -0.0002

Data Index: 798173 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1060. Min Act: -0.0002

Data Index: 215670 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1079. Min Act: -0.0002

Data Index: 729681 (C4 (Web Text))

Max Activating Token Index: 896