Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4029 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1468512 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1497149 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1468527 (Python Code)

Max Activating Token Index: 804

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1478778 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5384. Min Act: -0.0001

Data Index: 1516945 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1473589 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1608820 (Python Code)

Max Activating Token Index: 653

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1530622 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5203. Min Act: -0.0002

Data Index: 1397272 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4973. Min Act: -0.0001

Data Index: 1446108 (Python Code)

Max Activating Token Index: 495

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4825. Min Act: -0.0001

Data Index: 1489596 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1522246 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4752. Min Act: -0.0001

Data Index: 1430006 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1415421 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4728. Min Act: -0.0001

Data Index: 1385806 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1557159 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4340. Min Act: -0.0002

Data Index: 1525404 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4524. Min Act: -0.0001

Data Index: 1507681 (Python Code)

Max Activating Token Index: 772

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4768. Min Act: -0.0001

Data Index: 1405572 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4483. Min Act: -0.0001

Data Index: 1378786 (Python Code)

Max Activating Token Index: 808