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

Dataset: The Pile

Neuron 53 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0000

Data Index: 994409 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1891829 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1489735 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1884090 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1336562 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7406. Min Act: -0.0001

Data Index: 220186 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1152285 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7856. Min Act: -0.0000

Data Index: 450039 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7310. Min Act: -0.0000

Data Index: 457770 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7952. Min Act: -0.0000

Data Index: 682718 (The Pile)

Max Activating Token Index: 685

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7231. Min Act: -0.0000

Data Index: 89557 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1457751 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1250436 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6687. Min Act: -0.0000

Data Index: 352824 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6793. Min Act: -0.0000

Data Index: 912820 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1446309 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1455634 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6380. Min Act: -0.0000

Data Index: 783870 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.5960. Min Act: -0.0000

Data Index: 309268 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.6691. Min Act: -0.0000

Data Index: 433299 (The Pile)

Max Activating Token Index: 306