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

Dataset: The Pile

Neuron 1273 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: 1.2724. Min Range: -1.2724

Max Act: 1.2724. Min Act: -0.0000

Data Index: 468570 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1231760 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0021. Min Act: -0.0000

Data Index: 367790 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1414657 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1825138 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9179. Min Act: -0.0000

Data Index: 635726 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8661. Min Act: -0.0000

Data Index: 466464 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8302. Min Act: -0.0000

Data Index: 857099 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8293. Min Act: -0.0000

Data Index: 286028 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1382974 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1716349 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1649489 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1445943 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1398736 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7865. Min Act: -0.0000

Data Index: 662307 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1747381 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1792508 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1874353 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1906249 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7907. Min Act: -0.0000

Data Index: 258641 (The Pile)

Max Activating Token Index: 331