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

Dataset: The Pile

Neuron 4880 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: 0.6628. Min Range: -0.6628

Max Act: 0.6628. Min Act: -0.0000

Data Index: 184731 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1042492 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1119703 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4223. Min Act: -0.0000

Data Index: 939498 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4450. Min Act: -0.0000

Data Index: 240269 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1614151 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1738032 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4373. Min Act: -0.0000

Data Index: 276596 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1183586 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1653748 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4647. Min Act: -0.0000

Data Index: 884521 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4385. Min Act: -0.0000

Data Index: 172697 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4302. Min Act: 0.0000

Data Index: 1197910 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3434. Min Act: -0.0000

Data Index: 814259 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3752. Min Act: -0.0000

Data Index: 241739 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3874. Min Act: -0.0000

Data Index: 455228 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3839. Min Act: -0.0000

Data Index: 804236 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4255. Min Act: -0.0000

Data Index: 81667 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3834. Min Act: -0.0000

Data Index: 922646 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3778. Min Act: -0.0000

Data Index: 590059 (The Pile)

Max Activating Token Index: 631