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

Dataset: The Pile

Neuron 111 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0705. Min Range: -1.0705

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1558109 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.9141. Min Act: -0.0000

Data Index: 271961 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8255. Min Act: -0.0000

Data Index: 341763 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8383. Min Act: -0.0000

Data Index: 610459 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1278726 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1252656 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8660. Min Act: -0.0000

Data Index: 741672 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8904. Min Act: -0.0000

Data Index: 514868 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1789969 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8744. Min Act: -0.0000

Data Index: 19502 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1104931 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1087437 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1148735 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1123153 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7981. Min Act: -0.0000

Data Index: 588240 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1567841 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7546. Min Act: -0.0000

Data Index: 761544 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8172. Min Act: -0.0000

Data Index: 794879 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1116308 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1757894 (The Pile)

Max Activating Token Index: 475