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

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

Neuron 1860 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1403091 (Python Code)

Max Activating Token Index: 360

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1453662 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1592974 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1506450 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1625166 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1418480 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1637215 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1469756 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1550844 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1516463 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1542611 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1470766 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1606842 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1367565 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1395145 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1378397 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3259. Min Act: -0.0001

Data Index: 1634739 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1457680 (Python Code)

Max Activating Token Index: 599

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1655080 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1643981 (Python Code)

Max Activating Token Index: 49