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

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

Neuron 3972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1130777 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7381. Min Act: -0.0000

Data Index: 106909 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.6755. Min Act: -0.0000

Data Index: 623177 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.6244. Min Act: -0.0000

Data Index: 171008 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.4977. Min Act: -0.0000

Data Index: 1159012 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.4545. Min Act: -0.0000

Data Index: 734019 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.4654. Min Act: -0.0000

Data Index: 211067 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.4251. Min Act: -0.0000

Data Index: 762100 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.3864. Min Act: -0.0000

Data Index: 938277 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.4444. Min Act: -0.0000

Data Index: 301483 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.3713. Min Act: -0.0000

Data Index: 600827 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2948. Min Act: -0.0000

Data Index: 112184 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1071022 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2326. Min Act: -0.0000

Data Index: 989536 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.1666. Min Act: -0.0000

Data Index: 952765 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1017980 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2910. Min Act: -0.0000

Data Index: 156084 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.1461. Min Act: -0.0000

Data Index: 683149 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.1836. Min Act: -0.0000

Data Index: 769475 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.2472. Min Act: -0.0000

Data Index: 822463 (C4 (Web Text))

Max Activating Token Index: 319