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

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

Neuron 5650 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.5742. Min Act: -0.0000

Data Index: 620661 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1216774 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.3761. Min Act: -0.0000

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.2709. Min Act: -0.0000

Data Index: 15047 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.2625. Min Act: -0.0000

Data Index: 699149 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1243520 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.2868. Min Act: -0.0000

Data Index: 376161 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.2051. Min Act: -0.0000

Data Index: 548100 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1076008 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1371. Min Act: -0.0000

Data Index: 737748 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1103. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1136468 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1225309 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.0869. Min Act: -0.0000

Data Index: 245932 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.5742. Min Range: -1.5742

Max Act: 0.9988. Min Act: -0.0000

Data Index: 618837 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1052469 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1192. Min Act: -0.0000

Data Index: 873067 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1304325 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.5742. Min Range: -1.5742

Max Act: 1.0809. Min Act: -0.0000

Data Index: 303457 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.5742. Min Range: -1.5742

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1023935 (C4 (Web Text))

Max Activating Token Index: 861