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

Dataset: The Pile

Neuron 2895 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: 1.5982. Min Range: -1.5982

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1411177 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4644. Min Act: -0.0000

Data Index: 399992 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1027110 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.3382. Min Act: -0.0000

Data Index: 741094 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1104183 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1128621 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.3782. Min Act: -0.0000

Data Index: 761971 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1072189 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1734576 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0820. Min Act: -0.0000

Data Index: 628829 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1550481 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1575. Min Act: -0.0000

Data Index: 620681 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2959. Min Act: -0.0000

Data Index: 752171 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1267781 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1211. Min Act: -0.0000

Data Index: 233100 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1245. Min Act: -0.0000

Data Index: 437220 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1148928 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1642. Min Act: -0.0000

Data Index: 955987 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1219619 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1745934 (The Pile)

Max Activating Token Index: 448