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

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

Neuron 4366 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5307. Min Act: -0.0000

Data Index: 104263 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5804. Min Act: -0.0000

Data Index: 816953 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5488. Min Act: -0.0000

Data Index: 222790 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5436. Min Act: -0.0000

Data Index: 968604 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5361. Min Act: -0.0000

Data Index: 185930 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5275. Min Act: 0.0000

Data Index: 1033145 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4761. Min Act: -0.0000

Data Index: 972281 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4445. Min Act: -0.0000

Data Index: 744636 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4648. Min Act: -0.0000

Data Index: 792342 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4611. Min Act: -0.0000

Data Index: 757928 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4658. Min Act: -0.0000

Data Index: 390060 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4419. Min Act: -0.0000

Data Index: 667052 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4196. Min Act: -0.0000

Data Index: 969096 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4490. Min Act: -0.0000

Data Index: 199633 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1033179 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4427. Min Act: -0.0000

Data Index: 286974 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1291644 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4569. Min Act: -0.0000

Data Index: 84107 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4452. Min Act: 0.0001

Data Index: 973084 (C4 (Web Text))

Max Activating Token Index: 20