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

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

Neuron 5324 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1110749 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1492408 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1385436 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1545611 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1375891 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1205748 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1610122 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1150843 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1394947 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5007. Min Act: -0.0000

Data Index: 228983 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5205. Min Act: -0.0000

Data Index: 897204 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1423055 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1034139 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1277733 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1408493 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4636. Min Act: -0.0000

Data Index: 466290 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1044570 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5634. Min Act: -0.0000

Data Index: 60630 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1558279 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1559088 (Python Code)

Max Activating Token Index: 547