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

Dataset: The Pile

Neuron 3154 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.9151. Min Act: -0.0000

Data Index: 226542 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.7166. Min Act: -0.0000

Data Index: 485726 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.7844. Min Act: -0.0000

Data Index: 226994 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.7398. Min Act: -0.0000

Data Index: 738788 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.7450. Min Act: -0.0000

Data Index: 1403359 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.4288. Min Act: -0.0000

Data Index: 1924860 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.5721. Min Act: -0.0000

Data Index: 1778342 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.4037. Min Act: -0.0000

Data Index: 122145 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1786696 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.5253. Min Act: -0.0000

Data Index: 299222 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3418. Min Act: -0.0000

Data Index: 377220 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3583. Min Act: -0.0000

Data Index: 1396464 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3423. Min Act: -0.0000

Data Index: 993615 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.4933. Min Act: -0.0000

Data Index: 763716 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.6517. Min Act: -0.0000

Data Index: 639106 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.4709. Min Act: -0.0000

Data Index: 861638 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3087. Min Act: -0.0000

Data Index: 1229387 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.4136. Min Act: -0.0000

Data Index: 865940 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3452. Min Act: -0.0000

Data Index: 485190 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 3.9151. Min Range: -3.9151

Max Act: 3.3235. Min Act: -0.0000

Data Index: 120247 (The Pile)

Max Activating Token Index: 937