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

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

Neuron 4356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1389100 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1493860 (Python Code)

Max Activating Token Index: 623

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1481909 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1603071 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1452984 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1362925 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1579607 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2552. Min Act: 0.0000

Data Index: 218548 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1617143 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1377844 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2281. Min Act: -0.0000

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1491147 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1446108 (Python Code)

Max Activating Token Index: 102

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1654065 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1468626 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1524183 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1478903 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1433601 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1541267 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1407131 (Python Code)

Max Activating Token Index: 40