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

Dataset: The Pile

Neuron 2727 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: 0.4979. Min Range: -0.4979

Max Act: 0.4887. Min Act: -0.0000

Data Index: 2867 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4979. Min Act: -0.0000

Data Index: 68621 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1250548 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3857. Min Act: -0.0000

Data Index: 995612 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3619. Min Act: -0.0000

Data Index: 797159 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4262. Min Act: -0.0000

Data Index: 395936 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1205918 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1534503 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1190268 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3489. Min Act: -0.0000

Data Index: 904134 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1154581 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3660. Min Act: -0.0000

Data Index: 67694 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3858. Min Act: -0.0000

Data Index: 881508 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3634. Min Act: -0.0000

Data Index: 406132 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3210. Min Act: -0.0000

Data Index: 492028 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1089352 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1074221 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1703657 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1828969 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3327. Min Act: -0.0000

Data Index: 19131 (The Pile)

Max Activating Token Index: 151