Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1383519 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4761. Min Act: -0.0000

Data Index: 431103 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1262926 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1700616 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3776. Min Act: -0.0000

Data Index: 130915 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1152324 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1040913 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3337. Min Act: -0.0000

Data Index: 52626 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3460. Min Act: -0.0000

Data Index: 891010 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1666020 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3289. Min Act: -0.0000

Data Index: 802342 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3268. Min Act: -0.0000

Data Index: 799288 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1838734 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3356. Min Act: -0.0000

Data Index: 104935 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3040. Min Act: -0.0000

Data Index: 905035 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1898622 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1127112 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.2915. Min Act: -0.0000

Data Index: 790945 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1064502 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 0.4761. Min Range: -0.4761

Max Act: 0.2945. Min Act: -0.0000

Data Index: 869890 (The Pile)

Max Activating Token Index: 941