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

Dataset: The Pile

Neuron 2736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.1052. Min Act: -0.0000

Data Index: 933948 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1582208 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0705. Min Act: -0.0000

Data Index: 743806 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1220517 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0635. Min Act: -0.0000

Data Index: 918684 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1765510 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1044252 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1040947 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0532. Min Act: -0.0000

Data Index: 803870 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1509384 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0246. Min Act: -0.0000

Data Index: 342982 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1543157 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1258554 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0061. Min Act: -0.0000

Data Index: 557785 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1414217 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1133761 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9580. Min Act: -0.0000

Data Index: 945754 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1629429 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1639247 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1584602 (The Pile)

Max Activating Token Index: 836