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

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

Neuron 2442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.8434. Min Act: -0.0000

Data Index: 1433459 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1465430 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1425544 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1612704 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1558099 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1591616 (Python Code)

Max Activating Token Index: 587

Text #6

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1361704 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1649781 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1476626 (Python Code)

Max Activating Token Index: 931

Text #9

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1384010 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1528177 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1458570 (Python Code)

Max Activating Token Index: 761

Text #12

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1309743 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1413733 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1634701 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1637418 (Python Code)

Max Activating Token Index: 1021

Text #16

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1622001 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1476402 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1429813 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 1.8434. Min Range: -1.8434

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1646849 (Python Code)

Max Activating Token Index: 474