Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0000

Data Index: 928406 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1427. Min Act: -0.0000

Data Index: 826843 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1120. Min Act: -0.0000

Data Index: 368105 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0812. Min Act: -0.0000

Data Index: 633728 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0659. Min Act: -0.0000

Data Index: 747151 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0728. Min Act: -0.0000

Data Index: 597236 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1069704 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1165227 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0694. Min Act: -0.0000

Data Index: 789170 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0664. Min Act: -0.0000

Data Index: 907160 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1081630 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1116205 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0577. Min Act: -0.0000

Data Index: 372084 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0578. Min Act: -0.0000

Data Index: 414289 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0552. Min Act: -0.0000

Data Index: 543210 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1542849 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0536. Min Act: -0.0000

Data Index: 335613 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1019546 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1358234 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.0650. Min Act: -0.0000

Data Index: 119595 (C4 (Web Text))

Max Activating Token Index: 891