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

Dataset: The Pile

Neuron 3032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0000

Data Index: 69036 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6468. Min Act: -0.0000

Data Index: 558224 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1332880 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1358093 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1473801 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6160. Min Act: -0.0000

Data Index: 217192 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1802841 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6102. Min Act: -0.0000

Data Index: 636196 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6039. Min Act: -0.0000

Data Index: 620465 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1409969 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5442. Min Act: -0.0000

Data Index: 30899 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1789731 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4611. Min Act: -0.0000

Data Index: 892128 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5333. Min Act: -0.0000

Data Index: 95043 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5102. Min Act: -0.0000

Data Index: 601737 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5762. Min Act: -0.0000

Data Index: 44449 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1700897 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5115. Min Act: -0.0000

Data Index: 939583 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1495272 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4959. Min Act: -0.0000

Data Index: 928860 (The Pile)

Max Activating Token Index: 136