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

Dataset: The Pile

Neuron 2027 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: 3.7521. Min Range: -3.7521

Max Act: 3.2381. Min Act: -0.0000

Data Index: 1837737 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1794340 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.7521. Min Act: -0.0000

Data Index: 1894246 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.7163. Min Act: -0.0000

Data Index: 148100 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.1394. Min Act: -0.0000

Data Index: 1104183 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.8704. Min Act: 0.0000

Data Index: 922604 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.9537. Min Act: -0.0000

Data Index: 178998 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.2714. Min Act: -0.0000

Data Index: 517992 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.8984. Min Act: 0.0000

Data Index: 1855816 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.6153. Min Act: -0.0000

Data Index: 1006242 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.0261. Min Act: -0.0000

Data Index: 755656 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.1825. Min Act: 0.0000

Data Index: 299172 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.0065. Min Act: -0.0000

Data Index: 1247640 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.7285. Min Act: -0.0000

Data Index: 293585 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.4241. Min Act: -0.0000

Data Index: 1548023 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.9476. Min Act: -0.0000

Data Index: 510669 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.9399. Min Act: -0.0000

Data Index: 839442 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 3.7521. Min Range: -3.7521

Max Act: 2.4739. Min Act: -0.0000

Data Index: 848251 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.3745. Min Act: -0.0000

Data Index: 228495 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.0160. Min Act: -0.0000

Data Index: 765808 (The Pile)

Max Activating Token Index: 453