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

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

Neuron 1613 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: 0.4600. Min Range: -0.4600

Max Act: 0.4515. Min Act: -0.0000

Data Index: 204128 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1557687 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1581677 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1573645 (Python Code)

Max Activating Token Index: 806

Text #4

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4600. Min Act: -0.0000

Data Index: 900941 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1455691 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1477131 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4136. Min Act: -0.0000

Data Index: 186834 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1154624 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3932. Min Act: -0.0000

Data Index: 442741 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4129. Min Act: -0.0000

Data Index: 227509 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3963. Min Act: -0.0000

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4099. Min Act: -0.0000

Data Index: 944317 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1513778 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3695. Min Act: -0.0000

Data Index: 50428 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3886. Min Act: -0.0000

Data Index: 65007 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1545177 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1159990 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3364. Min Act: -0.0000

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1650725 (Python Code)

Max Activating Token Index: 364