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

Dataset: The Pile

Neuron 4037 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: 1.4260. Min Range: -1.4260

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1852273 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3257. Min Act: -0.0000

Data Index: 985112 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.4260. Min Act: -0.0000

Data Index: 1178238 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 1.4260. Min Range: -1.4260

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1462828 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3506. Min Act: -0.0000

Data Index: 517287 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1477806 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1652235 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1958213 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3092. Min Act: -0.0000

Data Index: 94663 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1247491 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1275236 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3789. Min Act: -0.0000

Data Index: 323450 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1916. Min Act: -0.0000

Data Index: 930696 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2322. Min Act: -0.0000

Data Index: 318416 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2808. Min Act: -0.0000

Data Index: 399705 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3079. Min Act: -0.0000

Data Index: 92409 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1938322 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1701162 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1509577 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2523. Min Act: -0.0000

Data Index: 848739 (The Pile)

Max Activating Token Index: 773