Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1441 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.6685. Min Act: -0.0000

Data Index: 694073 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4667. Min Act: -0.0000

Data Index: 153924 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1429181 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1859940 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4342. Min Act: -0.0000

Data Index: 734116 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4160. Min Act: -0.0000

Data Index: 101640 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1800528 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4250. Min Act: -0.0000

Data Index: 773808 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4129. Min Act: -0.0000

Data Index: 375493 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1352527 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3958. Min Act: -0.0000

Data Index: 361291 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3834. Min Act: -0.0000

Data Index: 705495 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1632788 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3775. Min Act: -0.0000

Data Index: 220523 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3762. Min Act: -0.0000

Data Index: 653447 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3840. Min Act: -0.0000

Data Index: 820316 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1066832 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3740. Min Act: -0.0000

Data Index: 624606 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1624288 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1754153 (The Pile)

Max Activating Token Index: 686