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

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

Neuron 5068 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: 6.4988. Min Range: -6.4988

Max Act: 6.4988. Min Act: -0.0000

Data Index: 12390 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 6.4988. Min Range: -6.4988

Max Act: 6.4164. Min Act: -0.0000

Data Index: 1054814 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1315819 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.4858. Min Act: -0.0000

Data Index: 1100436 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.1986. Min Act: -0.0000

Data Index: 788357 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.3710. Min Act: -0.0000

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.0991. Min Act: -0.0000

Data Index: 179132 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.8213. Min Act: -0.0000

Data Index: 43591 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.0707. Min Act: -0.0000

Data Index: 1126176 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.0550. Min Act: -0.0000

Data Index: 670320 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.8295. Min Act: -0.0000

Data Index: 1327633 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.0909. Min Act: -0.0000

Data Index: 460210 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.7912. Min Act: -0.0000

Data Index: 655757 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.7671. Min Act: -0.0000

Data Index: 813691 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.7401. Min Act: -0.0000

Data Index: 824003 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.5617. Min Act: -0.0000

Data Index: 956740 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.6765. Min Act: -0.0000

Data Index: 1282666 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.8252. Min Act: -0.0000

Data Index: 472631 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.6365. Min Act: 0.0000

Data Index: 344893 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 6.4988. Min Range: -6.4988

Max Act: 3.7674. Min Act: -0.0000

Data Index: 1291481 (C4 (Web Text))

Max Activating Token Index: 158