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

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

Neuron 3243 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1466195 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0823. Min Act: -0.0001

Data Index: 1614905 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9814. Min Act: -0.0001

Data Index: 1640896 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1593400 (Python Code)

Max Activating Token Index: 379

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1596099 (Python Code)

Max Activating Token Index: 644

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9085. Min Act: -0.0001

Data Index: 1448782 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9145. Min Act: -0.0001

Data Index: 1575089 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9139. Min Act: -0.0001

Data Index: 1553753 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1506861 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1504793 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1369941 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1428199 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1381419 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8798. Min Act: -0.0001

Data Index: 1601782 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8771. Min Act: -0.0001

Data Index: 1529069 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8663. Min Act: -0.0001

Data Index: 1649661 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8557. Min Act: -0.0001

Data Index: 1431253 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9940. Min Act: -0.0001

Data Index: 1578440 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8760. Min Act: -0.0001

Data Index: 1558909 (Python Code)

Max Activating Token Index: 578

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1655473 (Python Code)

Max Activating Token Index: 501