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

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

Neuron 4461 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: 1.3663. Min Range: -1.3663

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1113345 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1353882 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1263892 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1350471 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.3663. Min Range: -1.3663

Max Act: 1.0227. Min Act: -0.0000

Data Index: 875075 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9305. Min Act: -0.0000

Data Index: 630368 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1293398 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9499. Min Act: -0.0000

Data Index: 53086 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8450. Min Act: -0.0000

Data Index: 75698 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9204. Min Act: -0.0000

Data Index: 136375 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8909. Min Act: -0.0000

Data Index: 831269 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.9021. Min Act: -0.0000

Data Index: 610487 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8802. Min Act: -0.0000

Data Index: 885461 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8669. Min Act: -0.0000

Data Index: 559433 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8643. Min Act: -0.0000

Data Index: 760476 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8287. Min Act: -0.0000

Data Index: 460194 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1218370 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8464. Min Act: -0.0000

Data Index: 642209 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8368. Min Act: -0.0000

Data Index: 846311 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.3663. Min Range: -1.3663

Max Act: 0.8083. Min Act: -0.0000

Data Index: 703656 (C4 (Web Text))

Max Activating Token Index: 599