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

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

Neuron 1571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1612. Min Range: -2.1612

Max Act: 2.1612. Min Act: -0.0000

Data Index: 553890 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.1612. Min Range: -2.1612

Max Act: 2.0035. Min Act: -0.0000

Data Index: 870727 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 2.1612. Min Range: -2.1612

Max Act: 2.0031. Min Act: -0.0000

Data Index: 152242 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.1612. Min Range: -2.1612

Max Act: 2.0499. Min Act: -0.0000

Data Index: 216681 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.9044. Min Act: -0.0000

Data Index: 1316274 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7069. Min Act: -0.0000

Data Index: 697233 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.8128. Min Act: -0.0001

Data Index: 1204425 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7086. Min Act: -0.0000

Data Index: 315570 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.8081. Min Act: -0.0000

Data Index: 5376 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.6961. Min Act: -0.0000

Data Index: 211975 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7546. Min Act: -0.0000

Data Index: 936423 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7213. Min Act: -0.0000

Data Index: 18750 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7066. Min Act: -0.0001

Data Index: 1330456 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.6692. Min Act: -0.0000

Data Index: 22033 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7514. Min Act: -0.0000

Data Index: 1062127 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.7170. Min Act: -0.0000

Data Index: 811379 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.6183. Min Act: -0.0000

Data Index: 241790 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.6006. Min Act: -0.0001

Data Index: 208211 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.6240. Min Act: -0.0001

Data Index: 489621 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 2.1612. Min Range: -2.1612

Max Act: 1.5151. Min Act: -0.0000

Data Index: 533660 (C4 (Web Text))

Max Activating Token Index: 676