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

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

Neuron 2990 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4467. Min Act: -0.0000

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4192. Min Act: -0.0000

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4206. Min Act: -0.0000

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1330817 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1460459 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1592285 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1466537 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1631647 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1646352 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1462382 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1482824 (Python Code)

Max Activating Token Index: 201

Text #12

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1131648 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1416812 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1541030 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2544. Min Act: -0.0000

Data Index: 15938 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1537095 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1592024 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1371935 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1515617 (Python Code)

Max Activating Token Index: 39