Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 671 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1438602 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1009523 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0050. Min Act: -0.0006

Data Index: 216418 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1617567 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0045. Min Act: -0.0005

Data Index: 1046442 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1391893 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0040. Min Act: -0.0005

Data Index: 238147 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0040. Min Act: -0.0006

Data Index: 74947 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1562082 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1513650 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0036. Min Act: -0.0006

Data Index: 245979 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1395724 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0036. Min Act: -0.0006

Data Index: 111970 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1648435 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0034. Min Act: -0.0005

Data Index: 1579566 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1479715 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1576531 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1587645 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0034. Min Act: -0.0006

Data Index: 678525 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1389471 (Python Code)

Max Activating Token Index: 367