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

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

Neuron 927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2303. Min Act: -0.0002

Data Index: 635710 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2064. Min Act: -0.0002

Data Index: 226288 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1956. Min Act: -0.0002

Data Index: 1209434 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1755. Min Act: -0.0002

Data Index: 254443 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1735. Min Act: -0.0002

Data Index: 616284 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1296192 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1744. Min Act: -0.0002

Data Index: 432913 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1677. Min Act: -0.0002

Data Index: 266266 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1651. Min Act: -0.0002

Data Index: 296057 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1646. Min Act: -0.0002

Data Index: 1098351 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1647. Min Act: -0.0002

Data Index: 423586 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1642. Min Act: -0.0002

Data Index: 706359 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1619. Min Act: -0.0002

Data Index: 221509 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1595. Min Act: -0.0002

Data Index: 320243 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1593. Min Act: -0.0002

Data Index: 840360 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1498. Min Act: -0.0002

Data Index: 356864 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1242689 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1535. Min Act: -0.0002

Data Index: 72259 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1519. Min Act: -0.0002

Data Index: 292905 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1560. Min Act: -0.0002

Data Index: 620544 (C4 (Web Text))

Max Activating Token Index: 897