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

Dataset: The Pile

Neuron 2170 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: 0.5121. Min Range: -0.5121

Max Act: 0.5121. Min Act: -0.0000

Data Index: 20042 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4825. Min Act: 0.0000

Data Index: 1021002 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1236653 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1233701 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4681. Min Act: 0.0000

Data Index: 1264056 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1140779 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4840. Min Act: 0.0000

Data Index: 720537 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1136240 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4529. Min Act: 0.0000

Data Index: 527302 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4568. Min Act: -0.0000

Data Index: 376920 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3931. Min Act: 0.0000

Data Index: 1312140 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1106578 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4339. Min Act: -0.0000

Data Index: 382201 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4674. Min Act: 0.0000

Data Index: 1926558 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4372. Min Act: 0.0000

Data Index: 296310 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4587. Min Act: 0.0000

Data Index: 1635247 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1157130 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4252. Min Act: -0.0000

Data Index: 60502 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4246. Min Act: -0.0000

Data Index: 584951 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4349. Min Act: 0.0002

Data Index: 1061999 (The Pile)

Max Activating Token Index: 395