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

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

Neuron 4397 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1563937 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1450722 (Python Code)

Max Activating Token Index: 963

Text #2

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.1818. Min Act: -0.0000

Data Index: 1428133 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.0831. Min Act: -0.0000

Data Index: 1428196 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.2234. Min Act: -0.0000

Data Index: 1642031 (Python Code)

Max Activating Token Index: 975

Text #5

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.0903. Min Act: -0.0000

Data Index: 1499516 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.9682. Min Act: -0.0000

Data Index: 1635838 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1377115 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1645665 (Python Code)

Max Activating Token Index: 997

Text #9

Max Range: 2.3558. Min Range: -2.3558

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1512881 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.8307. Min Act: -0.0000

Data Index: 1528192 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.9377. Min Act: -0.0000

Data Index: 1436991 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1418728 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1454540 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1645531 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.9136. Min Act: -0.0000

Data Index: 1590381 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1585144 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.7658. Min Act: -0.0000

Data Index: 1430941 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1507739 (Python Code)

Max Activating Token Index: 879

Text #19

Max Range: 2.3558. Min Range: -2.3558

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1480347 (Python Code)

Max Activating Token Index: 615