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

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

Neuron 1021 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: 1.1669. Min Range: -1.1669

Max Act: 1.1669. Min Act: -0.0001

Data Index: 1416113 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.1127. Min Act: -0.0001

Data Index: 1376037 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1431249 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9798. Min Act: -0.0001

Data Index: 1570181 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0979. Min Act: -0.0001

Data Index: 1538283 (Python Code)

Max Activating Token Index: 819

Text #5

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0163. Min Act: -0.0001

Data Index: 1601757 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1366033 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0046. Min Act: -0.0001

Data Index: 1505612 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1448363 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9902. Min Act: -0.0002

Data Index: 1412291 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0120. Min Act: -0.0001

Data Index: 1396091 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9710. Min Act: -0.0001

Data Index: 1413500 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1587063 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1612556 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1564503 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9566. Min Act: -0.0001

Data Index: 1591867 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1366842 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1653486 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9510. Min Act: -0.0001

Data Index: 1370291 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9771. Min Act: -0.0001

Data Index: 1446923 (Python Code)

Max Activating Token Index: 277