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

Dataset: The Pile

Neuron 3914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1754888 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2755. Min Act: -0.0000

Data Index: 673002 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1061652 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2979. Min Act: -0.0000

Data Index: 455782 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1909. Min Act: -0.0000

Data Index: 838012 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1262504 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1883805 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1819. Min Act: -0.0000

Data Index: 226100 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1190. Min Act: -0.0000

Data Index: 490443 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1574490 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1026150 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1206840 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 1.5020. Min Range: -1.5020

Max Act: 0.9586. Min Act: -0.0000

Data Index: 371874 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1278. Min Act: -0.0000

Data Index: 398848 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1371093 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0302. Min Act: -0.0000

Data Index: 942206 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0553. Min Act: -0.0000

Data Index: 82114 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1633231 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.5020. Min Range: -1.5020

Max Act: 0.9294. Min Act: -0.0000

Data Index: 809570 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1435649 (The Pile)

Max Activating Token Index: 605