Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1825. Min Act: -0.0001

Data Index: 672808 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1457027 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1642. Min Act: -0.0001

Data Index: 230990 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1629. Min Act: -0.0001

Data Index: 661335 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1651940 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1571164 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1373. Min Act: -0.0001

Data Index: 295066 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1400. Min Act: -0.0001

Data Index: 540120 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1141531 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1402. Min Act: -0.0001

Data Index: 979384 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1399. Min Act: -0.0001

Data Index: 487940 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1406. Min Act: -0.0001

Data Index: 502531 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1448526 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1369. Min Act: -0.0001

Data Index: 602047 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1376162 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1334260 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1552289 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1633088 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1209081 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1354. Min Act: -0.0001

Data Index: 236252 (C4 (Web Text))

Max Activating Token Index: 82