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

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

Neuron 1744 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.7347. Min Act: -0.0001

Data Index: 1598774 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6825. Min Act: -0.0001

Data Index: 1202608 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1437555 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1586671 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1440086 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1390565 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6474. Min Act: -0.0001

Data Index: 1576930 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1471319 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1430251 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6307. Min Act: -0.0001

Data Index: 1445427 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1425278 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1616232 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1507524 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1419991 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6608. Min Act: -0.0000

Data Index: 622984 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1653700 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6258. Min Act: -0.0001

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1458341 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1507246 (Python Code)

Max Activating Token Index: 566