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

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

Neuron 2475 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: 0.2136. Min Range: -0.2136

Max Act: 0.2136. Min Act: -0.0000

Data Index: 521270 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1926. Min Act: -0.0000

Data Index: 73249 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1051468 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1994. Min Act: -0.0000

Data Index: 86402 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1819. Min Act: -0.0000

Data Index: 368287 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1278861 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1273787 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1688. Min Act: -0.0000

Data Index: 184926 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1116670 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1633. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1176631 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1220039 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1658. Min Act: -0.0000

Data Index: 994323 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1500. Min Act: -0.0000

Data Index: 590056 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1084599 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1479. Min Act: -0.0000

Data Index: 345776 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1570. Min Act: -0.0000

Data Index: 181044 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1511. Min Act: -0.0000

Data Index: 841214 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1386787 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1470. Min Act: -0.0000

Data Index: 287060 (C4 (Web Text))

Max Activating Token Index: 695