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

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

Neuron 1956 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: 0.5495. Min Range: -0.5495

Max Act: 0.5495. Min Act: -0.0000

Data Index: 619511 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4301. Min Act: -0.0000

Data Index: 922624 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1121603 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3838. Min Act: -0.0000

Data Index: 19408 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1463995 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1028371 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3449. Min Act: -0.0000

Data Index: 112057 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3452. Min Act: -0.0001

Data Index: 734615 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1242304 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1096864 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3616. Min Act: -0.0001

Data Index: 981397 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3496. Min Act: -0.0000

Data Index: 100995 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1179671 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1136657 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3408. Min Act: -0.0000

Data Index: 641330 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1334938 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3472. Min Act: -0.0000

Data Index: 821640 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3442. Min Act: -0.0000

Data Index: 442650 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3207. Min Act: -0.0000

Data Index: 146828 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1610543 (Python Code)

Max Activating Token Index: 191