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

Dataset: The Pile

Neuron 1962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1704838 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5679. Min Act: -0.0000

Data Index: 532577 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5536. Min Act: 0.0001

Data Index: 868617 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5264. Min Act: -0.0000

Data Index: 263121 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1197241 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1553858 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1794035 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5132. Min Act: -0.0000

Data Index: 375778 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1924783 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4829. Min Act: -0.0000

Data Index: 311635 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4998. Min Act: -0.0000

Data Index: 55104 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5647. Min Act: -0.0000

Data Index: 446959 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1270888 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4347. Min Act: -0.0000

Data Index: 546711 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4805. Min Act: -0.0000

Data Index: 131279 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1792089 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4858. Min Act: -0.0000

Data Index: 413745 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1084690 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4760. Min Act: -0.0000

Data Index: 431980 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4813. Min Act: -0.0000

Data Index: 189562 (The Pile)

Max Activating Token Index: 891