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

Dataset: The Pile

Neuron 1369 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: 1.1073. Min Range: -1.1073

Max Act: 1.0480. Min Act: -0.0000

Data Index: 691584 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1147239 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1245677 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1867717 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1836434 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1367313 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1667692 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.7432. Min Act: -0.0000

Data Index: 978900 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1236271 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1674935 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1150643 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6370. Min Act: -0.0000

Data Index: 261141 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1762664 (The Pile)

Max Activating Token Index: 230

Text #13

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1015519 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.7229. Min Act: -0.0000

Data Index: 238885 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6964. Min Act: -0.0000

Data Index: 645327 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1186664 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1236231 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1513184 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.6422. Min Act: -0.0000

Data Index: 304436 (The Pile)

Max Activating Token Index: 210