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

Dataset: The Pile

Neuron 107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.7663. Min Act: -0.0000

Data Index: 788961 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.5644. Min Act: -0.0000

Data Index: 561703 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.5928. Min Act: -0.0000

Data Index: 294770 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1725922 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1760289 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.4076. Min Act: -0.0000

Data Index: 597127 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1282811 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3905. Min Act: 0.0000

Data Index: 982 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1555384 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1566618 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1694240 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3611. Min Act: -0.0000

Data Index: 90842 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3350. Min Act: -0.0000

Data Index: 988537 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3430. Min Act: -0.0000

Data Index: 196314 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1411478 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1225048 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1380557 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1654032 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1375152 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.2940. Min Act: -0.0000

Data Index: 427502 (The Pile)

Max Activating Token Index: 858