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

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

Neuron 1041 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.9882. Min Act: -0.0000

Data Index: 1518763 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.8439. Min Act: -0.0000

Data Index: 1367513 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.8241. Min Act: -0.0000

Data Index: 1591834 (Python Code)

Max Activating Token Index: 514

Text #3

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.6026. Min Act: -0.0000

Data Index: 1583181 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.4718. Min Act: -0.0000

Data Index: 1385278 (Python Code)

Max Activating Token Index: 517

Text #5

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1628336 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1545446 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1495. Min Act: -0.0000

Data Index: 1636915 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.2673. Min Act: -0.0000

Data Index: 1444595 (Python Code)

Max Activating Token Index: 658

Text #9

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0325. Min Act: -0.0000

Data Index: 1526051 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1489660 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1277. Min Act: -0.0000

Data Index: 1613399 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1185. Min Act: -0.0000

Data Index: 1418269 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1627114 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0905. Min Act: -0.0000

Data Index: 602740 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1664. Min Act: -0.0000

Data Index: 1408457 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1620160 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0460. Min Act: -0.0000

Data Index: 1397754 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1569147 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 2.9882. Min Range: -2.9882

Max Act: 2.1490. Min Act: -0.0000

Data Index: 1447069 (Python Code)

Max Activating Token Index: 370