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

Dataset: The Pile

Neuron 835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4192. Min Act: -0.0000

Data Index: 845780 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.8055. Min Act: -0.0000

Data Index: 1387554 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.0833. Min Act: -0.0000

Data Index: 1340292 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.1141. Min Act: -0.0000

Data Index: 39624 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.9216. Min Act: -0.0000

Data Index: 1083441 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.9265. Min Act: -0.0000

Data Index: 1351855 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.6529. Min Act: -0.0000

Data Index: 781857 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.8674. Min Act: -0.0000

Data Index: 760956 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.6664. Min Act: -0.0000

Data Index: 1571264 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.1075. Min Act: -0.0000

Data Index: 138085 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.7034. Min Act: -0.0000

Data Index: 993753 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.6839. Min Act: -0.0000

Data Index: 1393277 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1484436 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.6475. Min Act: -0.0000

Data Index: 621095 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.7431. Min Act: -0.0000

Data Index: 422836 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.4740. Min Act: -0.0000

Data Index: 422176 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.4557. Min Act: -0.0000

Data Index: 840045 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.1358. Min Act: -0.0000

Data Index: 1887374 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1069564 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 3.8055. Min Range: -3.8055

Max Act: 2.4306. Min Act: -0.0000

Data Index: 1537693 (The Pile)

Max Activating Token Index: 480