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

Dataset: The Pile

Neuron 82 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.4738. Min Act: -0.0000

Data Index: 277937 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1293656 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0394. Min Act: -0.0000

Data Index: 123622 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0106. Min Act: -0.0000

Data Index: 645524 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9985. Min Act: -0.0000

Data Index: 202198 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9960. Min Act: -0.0000

Data Index: 891375 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9897. Min Act: -0.0000

Data Index: 927367 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1097233 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8779. Min Act: -0.0000

Data Index: 932120 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8928. Min Act: -0.0000

Data Index: 589825 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1745977 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1545553 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8810. Min Act: -0.0000

Data Index: 310335 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1141177 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8243. Min Act: -0.0000

Data Index: 462072 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1338669 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1232245 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9331. Min Act: -0.0000

Data Index: 296482 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1661744 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8324. Min Act: -0.0000

Data Index: 528820 (The Pile)

Max Activating Token Index: 561