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

Dataset: The Pile

Neuron 1814 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: 0.5351. Min Range: -0.5351

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1279567 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5318. Min Act: -0.0000

Data Index: 793826 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1200775 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1095841 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4801. Min Act: 0.0000

Data Index: 738678 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4831. Min Act: -0.0000

Data Index: 315317 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1631679 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4544. Min Act: -0.0000

Data Index: 783007 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1801936 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4388. Min Act: -0.0000

Data Index: 625606 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1009621 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4271. Min Act: 0.0000

Data Index: 298078 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1376489 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1986041 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4153. Min Act: -0.0000

Data Index: 454401 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1235331 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4005. Min Act: -0.0000

Data Index: 162341 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1482480 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1630714 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1847357 (The Pile)

Max Activating Token Index: 816