Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0343. Min Range: -1.0343

Max Act: 1.0343. Min Act: -0.0001

Data Index: 1396206 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1577776 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9706. Min Act: -0.0001

Data Index: 1465138 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9751. Min Act: -0.0001

Data Index: 1383848 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9244. Min Act: -0.0001

Data Index: 1368042 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8970. Min Act: -0.0001

Data Index: 1534403 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1591423 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9174. Min Act: -0.0001

Data Index: 1452771 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1418770 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9426. Min Act: -0.0001

Data Index: 1629040 (Python Code)

Max Activating Token Index: 675

Text #10

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1370501 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1544544 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1557685 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8897. Min Act: -0.0001

Data Index: 1495405 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8832. Min Act: -0.0001

Data Index: 1525062 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1454467 (Python Code)

Max Activating Token Index: 619

Text #16

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1496822 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1590384 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9081. Min Act: -0.0001

Data Index: 1596429 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1485255 (Python Code)

Max Activating Token Index: 888