Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1693 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1633092 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1485997 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4943. Min Act: -0.0000

Data Index: 1546568 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1443391 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1521286 (Python Code)

Max Activating Token Index: 624

Text #5

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1377765 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1475303 (Python Code)

Max Activating Token Index: 186

Text #7

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3951. Min Act: -0.0000

Data Index: 1451763 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1458394 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1524911 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1539136 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1487096 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1480290 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3493. Min Act: -0.0000

Data Index: 1615485 (Python Code)

Max Activating Token Index: 425

Text #14

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3788. Min Act: -0.0000

Data Index: 1466597 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1603734 (Python Code)

Max Activating Token Index: 521

Text #16

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1601834 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1601572 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1609231 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 1.5880. Min Range: -1.5880

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1635778 (Python Code)

Max Activating Token Index: 250