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

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

Neuron 3857 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: 0.2505. Min Range: -0.2505

Max Act: 0.2505. Min Act: -0.0002

Data Index: 870025 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2162. Min Act: -0.0002

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2073. Min Act: -0.0002

Data Index: 512433 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1862. Min Act: -0.0002

Data Index: 70508 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1969. Min Act: -0.0002

Data Index: 296306 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1918. Min Act: -0.0002

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1886. Min Act: -0.0002

Data Index: 105536 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1523. Min Act: -0.0002

Data Index: 839662 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1588. Min Act: -0.0002

Data Index: 1353680 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1485. Min Act: -0.0002

Data Index: 785819 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1473. Min Act: -0.0002

Data Index: 360839 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1462. Min Act: -0.0002

Data Index: 359771 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1085133 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1388. Min Act: -0.0002

Data Index: 63525 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1417. Min Act: -0.0002

Data Index: 762065 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1054699 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1404. Min Act: -0.0002

Data Index: 1127844 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1344. Min Act: -0.0002

Data Index: 760568 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1316. Min Act: -0.0002

Data Index: 407917 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1424. Min Act: -0.0002

Data Index: 1129077 (C4 (Web Text))

Max Activating Token Index: 755