Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 859 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1381354 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3173. Min Act: -0.0001

Data Index: 1456688 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1451430 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3225. Min Act: -0.0001

Data Index: 1604931 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1644. Min Act: -0.0001

Data Index: 1571259 (Python Code)

Max Activating Token Index: 787

Text #5

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1859. Min Act: -0.0001

Data Index: 1420062 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1814. Min Act: -0.0001

Data Index: 1541692 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1927. Min Act: -0.0001

Data Index: 1529291 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1508. Min Act: -0.0001

Data Index: 1502321 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1173. Min Act: -0.0001

Data Index: 1564590 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0390. Min Act: -0.0002

Data Index: 1511113 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1439755 (Python Code)

Max Activating Token Index: 229

Text #12

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0976. Min Act: -0.0001

Data Index: 1428871 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1638029 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9940. Min Act: -0.0001

Data Index: 1617805 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0215. Min Act: -0.0001

Data Index: 1398010 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0446. Min Act: -0.0001

Data Index: 1530819 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1655149 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1635. Min Act: -0.0001

Data Index: 1420273 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0185. Min Act: -0.0001

Data Index: 1457856 (Python Code)

Max Activating Token Index: 391