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

Dataset: The Pile

Neuron 2455 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: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1830463 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1367696 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1297. Min Act: -0.0000

Data Index: 848852 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1125281 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1488899 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1241. Min Act: -0.0000

Data Index: 68068 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1197. Min Act: -0.0000

Data Index: 396795 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1473985 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1042. Min Act: -0.0000

Data Index: 391865 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1028. Min Act: -0.0000

Data Index: 824068 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1185457 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1041. Min Act: -0.0000

Data Index: 602863 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1275373 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1008. Min Act: -0.0000

Data Index: 85244 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1016. Min Act: -0.0000

Data Index: 102918 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1777237 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.0997. Min Act: -0.0000

Data Index: 395337 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.0994. Min Act: -0.0000

Data Index: 336048 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1276945 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1499222 (The Pile)

Max Activating Token Index: 33