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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4322 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2699. Min Range: -2.2699

Max Act: 2.2699. Min Act: -0.0000

Data Index: 472299 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 2.2699. Min Range: -2.2699

Max Act: 2.2552. Min Act: -0.0000

Data Index: 663016 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 2.2699. Min Range: -2.2699

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1017769 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.9008. Min Act: -0.0000

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 2.2699. Min Range: -2.2699

Max Act: 2.0774. Min Act: -0.0000

Data Index: 772217 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7598. Min Act: -0.0000

Data Index: 21797 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.6694. Min Act: -0.0000

Data Index: 958792 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.8603. Min Act: -0.0000

Data Index: 1304506 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.8520. Min Act: -0.0000

Data Index: 544494 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1138830 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1208803 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.9028. Min Act: -0.0000

Data Index: 924466 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7944. Min Act: -0.0000

Data Index: 918294 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.8720. Min Act: -0.0000

Data Index: 1126844 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7229. Min Act: -0.0000

Data Index: 655181 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7345. Min Act: -0.0000

Data Index: 1242517 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.7757. Min Act: -0.0000

Data Index: 199133 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1081494 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1060666 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 2.2699. Min Range: -2.2699

Max Act: 1.6630. Min Act: -0.0000

Data Index: 899295 (C4 (Web Text))

Max Activating Token Index: 442