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

Dataset: The Pile

Neuron 3890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1218. Min Range: -1.1218

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1585221 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 1.1218. Min Range: -1.1218

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1619880 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1354300 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1930274 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.9326. Min Act: -0.0000

Data Index: 450672 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1714059 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.8429. Min Act: -0.0000

Data Index: 504545 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7655. Min Act: -0.0000

Data Index: 791240 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1880676 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1114920 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7332. Min Act: -0.0000

Data Index: 876772 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1871025 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7372. Min Act: -0.0000

Data Index: 234018 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.6575. Min Act: -0.0000

Data Index: 146188 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1220489 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7728. Min Act: -0.0000

Data Index: 940922 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7183. Min Act: -0.0000

Data Index: 426078 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.7187. Min Act: -0.0000

Data Index: 515064 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.6917. Min Act: -0.0000

Data Index: 53409 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 1.1218. Min Range: -1.1218

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1337526 (The Pile)

Max Activating Token Index: 348