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

Dataset: The Pile

Neuron 3573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7492. Min Act: -0.0000

Data Index: 357958 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1108354 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6815. Min Act: -0.0000

Data Index: 632671 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1794421 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1992190 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1866720 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1121538 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1544122 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1168591 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6270. Min Act: -0.0000

Data Index: 248727 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5690. Min Act: -0.0000

Data Index: 51724 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1625006 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1212018 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1035675 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1264396 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1537466 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5415. Min Act: -0.0000

Data Index: 618333 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1378372 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5326. Min Act: -0.0000

Data Index: 487343 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5515. Min Act: -0.0000

Data Index: 787189 (The Pile)

Max Activating Token Index: 596