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

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

Neuron 446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0002

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1626. Min Act: -0.0001

Data Index: 989183 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1603. Min Act: -0.0000

Data Index: 135327 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1545. Min Act: -0.0001

Data Index: 514768 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1547. Min Act: -0.0001

Data Index: 284239 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1588. Min Act: -0.0001

Data Index: 258678 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1552. Min Act: -0.0001

Data Index: 113401 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1475. Min Act: -0.0001

Data Index: 831021 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1512. Min Act: 0.0000

Data Index: 1303991 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1484. Min Act: 0.0002

Data Index: 1230555 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1460. Min Act: -0.0002

Data Index: 689767 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1502. Min Act: -0.0002

Data Index: 746698 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1384. Min Act: -0.0002

Data Index: 397217 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1525. Min Act: -0.0002

Data Index: 796418 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1439. Min Act: -0.0002

Data Index: 246367 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1469. Min Act: -0.0002

Data Index: 32210 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1472. Min Act: -0.0001

Data Index: 802175 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1446. Min Act: -0.0002

Data Index: 717448 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1073832 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1478. Min Act: 0.0000

Data Index: 525007 (C4 (Web Text))

Max Activating Token Index: 659