Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.4072. Min Act: -0.0000

Data Index: 1148099 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.3541. Min Act: -0.0000

Data Index: 1071332 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.0564. Min Act: -0.0000

Data Index: 963297 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.1019. Min Act: -0.0000

Data Index: 410986 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.2230. Min Act: -0.0000

Data Index: 255032 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.1524. Min Act: -0.0001

Data Index: 1103931 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.0081. Min Act: -0.0000

Data Index: 350531 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 2.4072. Min Range: -2.4072

Max Act: 2.0860. Min Act: -0.0000

Data Index: 992021 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.9793. Min Act: -0.0000

Data Index: 247403 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.9486. Min Act: -0.0000

Data Index: 1000771 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.8565. Min Act: -0.0000

Data Index: 336859 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.9035. Min Act: -0.0000

Data Index: 769566 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1091707 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.9773. Min Act: -0.0001

Data Index: 305290 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.8674. Min Act: -0.0000

Data Index: 320937 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.7120. Min Act: -0.0000

Data Index: 991989 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1002337 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.8655. Min Act: -0.0000

Data Index: 1072556 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.6717. Min Act: -0.0000

Data Index: 55411 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 2.4072. Min Range: -2.4072

Max Act: 1.7523. Min Act: -0.0000

Data Index: 934954 (C4 (Web Text))

Max Activating Token Index: 500