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

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

Neuron 639 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: 0.5886. Min Range: -0.5886

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1133158 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1066931 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1094050 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4254. Min Act: -0.0000

Data Index: 160004 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4297. Min Act: -0.0000

Data Index: 938136 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1225834 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4258. Min Act: -0.0000

Data Index: 136363 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4808. Min Act: -0.0000

Data Index: 512492 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4061. Min Act: -0.0000

Data Index: 407426 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3803. Min Act: -0.0000

Data Index: 907523 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4184. Min Act: -0.0000

Data Index: 738457 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1164809 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3716. Min Act: -0.0000

Data Index: 421962 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3863. Min Act: -0.0000

Data Index: 393663 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3814. Min Act: -0.0000

Data Index: 257265 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4067. Min Act: -0.0000

Data Index: 632459 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3691. Min Act: -0.0000

Data Index: 244558 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3818. Min Act: -0.0000

Data Index: 910852 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4050. Min Act: -0.0000

Data Index: 812319 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.3697. Min Act: -0.0000

Data Index: 825736 (C4 (Web Text))

Max Activating Token Index: 14