Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1711335 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1080781 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1463273 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1526. Min Act: -0.0000

Data Index: 10358 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1456. Min Act: -0.0000

Data Index: 426783 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1245066 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1935653 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1023805 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1402925 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1588178 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1511564 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1293. Min Act: -0.0000

Data Index: 555292 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1279914 (The Pile)

Max Activating Token Index: 230

Text #13

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1204682 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1983543 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1900278 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1617339 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1177. Min Act: -0.0000

Data Index: 383136 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1211. Min Act: -0.0000

Data Index: 562343 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1897205 (The Pile)

Max Activating Token Index: 642