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

Dataset: The Pile

Neuron 2639 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: 4.2768. Min Range: -4.2768

Max Act: 4.2768. Min Act: -0.0000

Data Index: 1962627 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 4.2768. Min Range: -4.2768

Max Act: 4.1199. Min Act: -0.0000

Data Index: 1370676 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 4.2768. Min Range: -4.2768

Max Act: 4.0352. Min Act: -0.0000

Data Index: 594305 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 4.2768. Min Range: -4.2768

Max Act: 4.1342. Min Act: -0.0000

Data Index: 1876606 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.8502. Min Act: -0.0000

Data Index: 1166435 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1227004 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.7577. Min Act: -0.0000

Data Index: 977045 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.5868. Min Act: -0.0000

Data Index: 1103010 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.6750. Min Act: -0.0000

Data Index: 1570488 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.6747. Min Act: -0.0000

Data Index: 491237 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.4916. Min Act: -0.0000

Data Index: 316514 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.3345. Min Act: -0.0000

Data Index: 316273 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.6342. Min Act: -0.0000

Data Index: 510421 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.4441. Min Act: -0.0000

Data Index: 1679895 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.4557. Min Act: -0.0000

Data Index: 220918 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.7011. Min Act: -0.0000

Data Index: 1386579 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.5716. Min Act: -0.0000

Data Index: 924156 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.6290. Min Act: -0.0000

Data Index: 1546919 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.3985. Min Act: -0.0000

Data Index: 1067764 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 4.2768. Min Range: -4.2768

Max Act: 3.5261. Min Act: -0.0000

Data Index: 1197184 (The Pile)

Max Activating Token Index: 74