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

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

Neuron 1361 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1624. Min Act: -0.0001

Data Index: 28393 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1572. Min Act: -0.0001

Data Index: 735877 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1481. Min Act: -0.0001

Data Index: 514922 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1374. Min Act: -0.0001

Data Index: 321554 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1147826 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1370147 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1117697 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1328128 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1172041 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1328. Min Act: -0.0001

Data Index: 883288 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1288. Min Act: -0.0001

Data Index: 307825 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1284. Min Act: -0.0001

Data Index: 796349 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1282. Min Act: -0.0001

Data Index: 393780 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1040362 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1413152 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1467947 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1610124 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1642244 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1411754 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1505649 (Python Code)

Max Activating Token Index: 376