Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 281 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1083338 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5462. Min Act: -0.0000

Data Index: 458135 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5137. Min Act: -0.0000

Data Index: 809252 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1898504 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5010. Min Act: -0.0000

Data Index: 964395 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4830. Min Act: -0.0000

Data Index: 214618 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4730. Min Act: -0.0000

Data Index: 631171 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4860. Min Act: -0.0000

Data Index: 926757 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1335412 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1460864 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1934132 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1504837 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4719. Min Act: -0.0000

Data Index: 38394 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1949033 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1584009 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.3992. Min Act: -0.0000

Data Index: 610498 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1043137 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1176512 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1628936 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4406. Min Act: -0.0000

Data Index: 492659 (The Pile)

Max Activating Token Index: 502