Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1259 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1376486 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1384632 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1547349 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1571288 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1536748 (Python Code)

Max Activating Token Index: 562

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1512384 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1594950 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1384733 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1465725 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1518913 (Python Code)

Max Activating Token Index: 412

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1511785 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1400235 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1641032 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1551182 (Python Code)

Max Activating Token Index: 588

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1420536 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1549999 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1542001 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1394743 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1519672 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1598944 (Python Code)

Max Activating Token Index: 50