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

Dataset: The Pile

Neuron 224 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: 3.4694. Min Range: -3.4694

Max Act: 3.4694. Min Act: -0.0000

Data Index: 1486975 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 3.4694. Min Range: -3.4694

Max Act: 3.1282. Min Act: -0.0000

Data Index: 1311176 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 3.4694. Min Range: -3.4694

Max Act: 3.0951. Min Act: -0.0000

Data Index: 668141 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.9788. Min Act: -0.0000

Data Index: 1963715 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.9274. Min Act: -0.0000

Data Index: 1448876 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.9058. Min Act: -0.0000

Data Index: 1948982 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.6286. Min Act: -0.0000

Data Index: 748122 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1024419 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.8564. Min Act: -0.0000

Data Index: 1394354 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.7208. Min Act: -0.0000

Data Index: 1620745 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.8112. Min Act: -0.0000

Data Index: 1336235 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.4210. Min Act: -0.0000

Data Index: 873471 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.5353. Min Act: -0.0000

Data Index: 615530 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.3710. Min Act: -0.0000

Data Index: 1423795 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.2672. Min Act: -0.0000

Data Index: 618841 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.2487. Min Act: -0.0000

Data Index: 513959 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.5754. Min Act: -0.0000

Data Index: 1109733 (The Pile)

Max Activating Token Index: 804

Text #17

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1653800 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.2315. Min Act: -0.0000

Data Index: 1652224 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 3.4694. Min Range: -3.4694

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1938016 (The Pile)

Max Activating Token Index: 834