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

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

Neuron 2819 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.2792. Min Act: -0.0000

Data Index: 1641241 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9651. Min Act: -0.0000

Data Index: 1375782 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.6159. Min Act: -0.0000

Data Index: 1556815 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.4622. Min Act: -0.0000

Data Index: 1467966 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.6055. Min Act: -0.0000

Data Index: 1479490 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.1281. Min Act: -0.0000

Data Index: 1650313 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.1641. Min Act: -0.0000

Data Index: 1557479 (Python Code)

Max Activating Token Index: 686

Text #7

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.8829. Min Act: -0.0000

Data Index: 1387235 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.6626. Min Act: -0.0000

Data Index: 1509193 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.8301. Min Act: -0.0000

Data Index: 1368893 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.7981. Min Act: -0.0000

Data Index: 1474769 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.7607. Min Act: -0.0000

Data Index: 1424019 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.6650. Min Act: -0.0000

Data Index: 1494880 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.4438. Min Act: -0.0000

Data Index: 1476094 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.6016. Min Act: -0.0000

Data Index: 1378581 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.2930. Min Act: -0.0000

Data Index: 1591107 (Python Code)

Max Activating Token Index: 511

Text #16

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.4019. Min Act: -0.0000

Data Index: 1389693 (Python Code)

Max Activating Token Index: 571

Text #17

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.4482. Min Act: -0.0000

Data Index: 1628126 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.4933. Min Act: -0.0000

Data Index: 1584986 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 5.2792. Min Range: -5.2792

Max Act: 3.3326. Min Act: -0.0000

Data Index: 1376970 (Python Code)

Max Activating Token Index: 197