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

Dataset: The Pile

Neuron 1246 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.6532. Min Act: -0.0000

Data Index: 699832 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.6191. Min Act: -0.0000

Data Index: 1592666 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.3252. Min Act: -0.0000

Data Index: 1957113 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.2438. Min Act: -0.0000

Data Index: 1801698 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.1379. Min Act: -0.0000

Data Index: 1105260 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.2128. Min Act: -0.0000

Data Index: 72308 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.3465. Min Act: -0.0000

Data Index: 322292 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.7520. Min Act: -0.0000

Data Index: 1918063 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.0186. Min Act: -0.0000

Data Index: 1782282 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.8983. Min Act: -0.0000

Data Index: 537736 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.9135. Min Act: -0.0000

Data Index: 1096036 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.8987. Min Act: -0.0000

Data Index: 636055 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.8641. Min Act: -0.0000

Data Index: 1349676 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.0104. Min Act: -0.0000

Data Index: 413277 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 3.6532. Min Range: -3.6532

Max Act: 3.0616. Min Act: -0.0000

Data Index: 1888790 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.7491. Min Act: -0.0000

Data Index: 522804 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.8018. Min Act: -0.0000

Data Index: 1680795 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.5265. Min Act: -0.0000

Data Index: 1359851 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.4398. Min Act: -0.0000

Data Index: 1768519 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 3.6532. Min Range: -3.6532

Max Act: 2.6661. Min Act: -0.0000

Data Index: 251971 (The Pile)

Max Activating Token Index: 395