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

Dataset: The Pile

Neuron 3193 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1918653 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7403. Min Act: -0.0000

Data Index: 512488 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1653644 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1443005 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6550. Min Act: 0.0000

Data Index: 1474824 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6477. Min Act: -0.0000

Data Index: 813106 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1211321 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5996. Min Act: -0.0000

Data Index: 831271 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6253. Min Act: -0.0000

Data Index: 731476 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6442. Min Act: -0.0000

Data Index: 293678 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6085. Min Act: -0.0000

Data Index: 232272 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1023658 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6411. Min Act: -0.0000

Data Index: 65027 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6205. Min Act: -0.0000

Data Index: 470785 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1395188 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1403251 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1495506 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5799. Min Act: -0.0000

Data Index: 236191 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5723. Min Act: -0.0000

Data Index: 251713 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1189964 (The Pile)

Max Activating Token Index: 1003