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

Dataset: The Pile

Neuron 1480 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: 3.3089. Min Range: -3.3089

Max Act: 3.1283. Min Act: -0.0000

Data Index: 189294 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.3066. Min Act: -0.0000

Data Index: 1133391 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.3089. Min Act: -0.0000

Data Index: 1288212 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2478. Min Act: -0.0000

Data Index: 307564 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2612. Min Act: -0.0000

Data Index: 518691 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8323. Min Act: -0.0001

Data Index: 1475272 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8092. Min Act: -0.0000

Data Index: 1331525 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8002. Min Act: -0.0000

Data Index: 44039 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.6243. Min Act: -0.0000

Data Index: 1505344 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9153. Min Act: -0.0000

Data Index: 1410538 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9026. Min Act: -0.0000

Data Index: 904832 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.7424. Min Act: -0.0000

Data Index: 110261 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8654. Min Act: -0.0000

Data Index: 1882236 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.7199. Min Act: -0.0000

Data Index: 55033 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8641. Min Act: -0.0000

Data Index: 1801014 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8486. Min Act: -0.0000

Data Index: 783257 (The Pile)

Max Activating Token Index: 667

Text #16

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.8558. Min Act: -0.0000

Data Index: 1285482 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.5488. Min Act: -0.0000

Data Index: 152817 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.5226. Min Act: -0.0000

Data Index: 483574 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.5395. Min Act: -0.0000

Data Index: 753677 (The Pile)

Max Activating Token Index: 859