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

Dataset: The Pile

Neuron 200 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: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: -0.0000

Data Index: 453411 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3548. Min Act: -0.0000

Data Index: 986178 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3266. Min Act: -0.0000

Data Index: 613910 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2991. Min Act: -0.0000

Data Index: 534543 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1932337 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2943. Min Act: -0.0000

Data Index: 65568 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1651999 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2530. Min Act: -0.0000

Data Index: 705440 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2880. Min Act: -0.0000

Data Index: 297063 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2954. Min Act: -0.0000

Data Index: 166944 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1362665 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2536. Min Act: -0.0000

Data Index: 194946 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2467. Min Act: -0.0000

Data Index: 331421 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1615331 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1292753 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1224274 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1854718 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2251. Min Act: -0.0000

Data Index: 459979 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1416136 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1396981 (The Pile)

Max Activating Token Index: 440