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

Dataset: The Pile

Neuron 1589 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1704248 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1504. Min Act: 0.0000

Data Index: 599909 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1516. Min Act: -0.0000

Data Index: 982305 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1930305 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1167196 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1430. Min Act: -0.0000

Data Index: 982993 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1034710 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1384. Min Act: -0.0000

Data Index: 220667 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1793352 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1378. Min Act: -0.0000

Data Index: 525299 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1230. Min Act: -0.0000

Data Index: 153052 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1364. Min Act: -0.0000

Data Index: 472040 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1052558 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1337. Min Act: -0.0000

Data Index: 501136 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1326. Min Act: -0.0000

Data Index: 421628 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1964640 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1362. Min Act: -0.0000

Data Index: 303808 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1027925 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1182828 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1302. Min Act: -0.0000

Data Index: 270203 (The Pile)

Max Activating Token Index: 352