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

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

Neuron 1465 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2547. Min Act: -0.0000

Data Index: 1515526 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.8954. Min Act: -0.0000

Data Index: 1613959 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1531423 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.3625. Min Act: -0.0000

Data Index: 1519796 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.3270. Min Act: -0.0000

Data Index: 1412391 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.3972. Min Act: -0.0000

Data Index: 1428827 (Python Code)

Max Activating Token Index: 811

Text #6

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2395. Min Act: -0.0000

Data Index: 1465722 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1571. Min Act: -0.0000

Data Index: 1405681 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1366098 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.3025. Min Act: -0.0000

Data Index: 1437217 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1473515 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1625685 (Python Code)

Max Activating Token Index: 603

Text #12

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2574. Min Act: -0.0000

Data Index: 1508667 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2476. Min Act: -0.0000

Data Index: 1387844 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1606. Min Act: -0.0000

Data Index: 1581027 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.2604. Min Act: -0.0000

Data Index: 1458396 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1473. Min Act: -0.0000

Data Index: 1420963 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1185. Min Act: -0.0000

Data Index: 1629166 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.0716. Min Act: -0.0000

Data Index: 1558638 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 3.2547. Min Range: -3.2547

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1491951 (Python Code)

Max Activating Token Index: 110