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

Dataset: The Pile

Neuron 87 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: 0.4846. Min Range: -0.4846

Max Act: 0.4846. Min Act: -0.0000

Data Index: 318372 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3920. Min Act: -0.0000

Data Index: 764987 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1607216 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1930001 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3802. Min Act: -0.0000

Data Index: 995403 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3841. Min Act: -0.0000

Data Index: 396914 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1225139 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1871773 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3938. Min Act: -0.0000

Data Index: 467211 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3924. Min Act: -0.0000

Data Index: 227263 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3791. Min Act: -0.0000

Data Index: 81450 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1860062 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4042. Min Act: -0.0000

Data Index: 307831 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3686. Min Act: -0.0000

Data Index: 510712 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3815. Min Act: -0.0000

Data Index: 766814 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1283831 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1643533 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3324. Min Act: -0.0000

Data Index: 904526 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1711583 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3500. Min Act: -0.0000

Data Index: 290072 (The Pile)

Max Activating Token Index: 846