Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3297 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1381975 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1613400 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4662. Min Act: -0.0001

Data Index: 1614533 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1555682 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1631803 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1401132 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1563594 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4000. Min Act: -0.0001

Data Index: 1542001 (Python Code)

Max Activating Token Index: 347

Text #8

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1519993 (Python Code)

Max Activating Token Index: 459

Text #9

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.4085. Min Act: -0.0001

Data Index: 1620127 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3992. Min Act: -0.0001

Data Index: 1558106 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1510455 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1620169 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1398880 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1649697 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1515506 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2534. Min Act: -0.0001

Data Index: 1369424 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3622. Min Act: -0.0001

Data Index: 1630528 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1546267 (Python Code)

Max Activating Token Index: 742

Text #19

Max Range: 1.5683. Min Range: -1.5683

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1564428 (Python Code)

Max Activating Token Index: 362