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

Dataset: The Pile

Neuron 1025 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: 3.7701. Min Range: -3.7701

Max Act: 3.6558. Min Act: -0.0000

Data Index: 1864837 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.7701. Min Act: -0.0000

Data Index: 1207562 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.5650. Min Act: -0.0000

Data Index: 282565 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.5411. Min Act: -0.0000

Data Index: 1186784 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.2619. Min Act: -0.0000

Data Index: 1021844 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.3752. Min Act: -0.0000

Data Index: 276957 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.4396. Min Act: -0.0000

Data Index: 829753 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.4488. Min Act: -0.0000

Data Index: 500663 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.2983. Min Act: -0.0000

Data Index: 1235106 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.4253. Min Act: -0.0000

Data Index: 168242 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.2342. Min Act: -0.0000

Data Index: 1757523 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.3495. Min Act: -0.0000

Data Index: 440395 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.0241. Min Act: -0.0000

Data Index: 925543 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.3221. Min Act: -0.0000

Data Index: 970989 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.1315. Min Act: -0.0000

Data Index: 382561 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.0272. Min Act: -0.0000

Data Index: 1275049 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.2272. Min Act: -0.0000

Data Index: 1502168 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.0717. Min Act: -0.0000

Data Index: 451793 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 3.7701. Min Range: -3.7701

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1428749 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 3.7701. Min Range: -3.7701

Max Act: 2.8943. Min Act: -0.0000

Data Index: 367863 (The Pile)

Max Activating Token Index: 720