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

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

Neuron 2846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.6066. Min Act: -0.0001

Data Index: 1477923 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1635594 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.5087. Min Act: -0.0001

Data Index: 1570380 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1472177 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.5005. Min Act: -0.0001

Data Index: 1545978 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1641309 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.5195. Min Act: -0.0001

Data Index: 1618951 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4996. Min Act: -0.0001

Data Index: 1610541 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1539283 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1533841 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1381546 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1370906 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4815. Min Act: -0.0001

Data Index: 1478495 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4355. Min Act: -0.0001

Data Index: 1633874 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1647322 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1414850 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1484143 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1425658 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4587. Min Act: -0.0001

Data Index: 1471309 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.6066. Min Range: -0.6066

Max Act: 0.4467. Min Act: -0.0001

Data Index: 1473970 (Python Code)

Max Activating Token Index: 130