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

Dataset: The Pile

Neuron 850 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: 3.7843. Min Range: -3.7843

Max Act: 3.6361. Min Act: -0.0000

Data Index: 1212887 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.7843. Min Act: 0.0000

Data Index: 1603332 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.6027. Min Act: 0.0000

Data Index: 685511 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.2423. Min Act: -0.0000

Data Index: 997990 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.6672. Min Act: -0.0000

Data Index: 898450 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.3276. Min Act: -0.0000

Data Index: 1669287 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.3406. Min Act: -0.0000

Data Index: 383206 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.1426. Min Act: -0.0000

Data Index: 198048 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.2235. Min Act: -0.0000

Data Index: 1561267 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0374. Min Act: -0.0000

Data Index: 1244183 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.1128. Min Act: -0.0000

Data Index: 628823 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.1244. Min Act: -0.0000

Data Index: 1747388 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.1139. Min Act: -0.0000

Data Index: 843326 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0714. Min Act: -0.0000

Data Index: 474811 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0825. Min Act: -0.0000

Data Index: 1724988 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0693. Min Act: -0.0000

Data Index: 749872 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0456. Min Act: -0.0000

Data Index: 194435 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0271. Min Act: -0.0000

Data Index: 161627 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 3.7843. Min Range: -3.7843

Max Act: 3.0205. Min Act: 0.0000

Data Index: 168806 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 3.7843. Min Range: -3.7843

Max Act: 2.9752. Min Act: -0.0000

Data Index: 1508628 (The Pile)

Max Activating Token Index: 101