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

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

Neuron 4909 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.3950. Min Act: -0.0000

Data Index: 570555 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1154182 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9047. Min Act: -0.0000

Data Index: 542481 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1325897 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1135565 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8089. Min Act: -0.0000

Data Index: 166825 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7576. Min Act: 0.0000

Data Index: 1342267 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7489. Min Act: -0.0000

Data Index: 810519 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7453. Min Act: -0.0000

Data Index: 167747 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7129. Min Act: -0.0000

Data Index: 820974 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7647. Min Act: -0.0000

Data Index: 99028 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7078. Min Act: -0.0000

Data Index: 508310 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7499. Min Act: -0.0000

Data Index: 312733 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6523. Min Act: -0.0000

Data Index: 162249 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.7251. Min Act: -0.0000

Data Index: 415336 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1196507 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6728. Min Act: -0.0000

Data Index: 222594 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6494. Min Act: -0.0000

Data Index: 529669 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6069. Min Act: -0.0000

Data Index: 700 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1096617 (C4 (Web Text))

Max Activating Token Index: 977