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

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

Neuron 5750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.9541. Min Act: -0.0000

Data Index: 1455587 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.7292. Min Act: -0.0000

Data Index: 1425403 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.7188. Min Act: -0.0000

Data Index: 1428917 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.5561. Min Act: -0.0000

Data Index: 1608371 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.6886. Min Act: -0.0000

Data Index: 1487600 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.6247. Min Act: -0.0000

Data Index: 1452447 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1614200 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.4668. Min Act: -0.0000

Data Index: 1384051 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1428882 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1580978 (Python Code)

Max Activating Token Index: 105

Text #10

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3712. Min Act: -0.0000

Data Index: 1612501 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.4505. Min Act: -0.0000

Data Index: 1604066 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1650186 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3749. Min Act: -0.0000

Data Index: 1556678 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.3573. Min Act: -0.0000

Data Index: 1484721 (Python Code)

Max Activating Token Index: 675

Text #15

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.2127. Min Act: -0.0000

Data Index: 1587051 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.1892. Min Act: -0.0000

Data Index: 1474758 (Python Code)

Max Activating Token Index: 816

Text #17

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.4345. Min Act: -0.0000

Data Index: 1614317 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.2964. Min Act: -0.0000

Data Index: 1565118 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 2.9541. Min Range: -2.9541

Max Act: 2.2925. Min Act: -0.0000

Data Index: 1597391 (Python Code)

Max Activating Token Index: 1008