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

Dataset: The Pile

Neuron 480 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0460. Min Range: -4.0460

Max Act: 4.0460. Min Act: -0.0000

Data Index: 1019580 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.8060. Min Act: -0.0000

Data Index: 433930 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.9194. Min Act: -0.0000

Data Index: 1193167 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.9555. Min Act: -0.0000

Data Index: 611500 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.7944. Min Act: -0.0000

Data Index: 1186618 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.6324. Min Act: -0.0000

Data Index: 382125 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.9178. Min Act: -0.0000

Data Index: 1919008 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.7369. Min Act: -0.0000

Data Index: 1358002 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.5740. Min Act: -0.0000

Data Index: 704139 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.5525. Min Act: -0.0000

Data Index: 724308 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.5786. Min Act: -0.0000

Data Index: 532636 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.8418. Min Act: -0.0000

Data Index: 916834 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.6631. Min Act: -0.0000

Data Index: 542732 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.8062. Min Act: -0.0000

Data Index: 1249907 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.5880. Min Act: -0.0000

Data Index: 209261 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.2761. Min Act: -0.0000

Data Index: 1109124 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.5257. Min Act: -0.0000

Data Index: 974284 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.3699. Min Act: -0.0000

Data Index: 814979 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.4662. Min Act: -0.0000

Data Index: 339646 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 4.0460. Min Range: -4.0460

Max Act: 3.4960. Min Act: -0.0000

Data Index: 367947 (The Pile)

Max Activating Token Index: 679