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

Dataset: The Pile

Neuron 4726 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.9115. Min Act: -0.0000

Data Index: 414262 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.8637. Min Act: -0.0000

Data Index: 378479 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.7191. Min Act: -0.0000

Data Index: 1481555 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6793. Min Act: -0.0000

Data Index: 1906122 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.7567. Min Act: -0.0000

Data Index: 237216 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1212649 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1931459 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1305146 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1868305 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.5112. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6050. Min Act: -0.0000

Data Index: 675973 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.5868. Min Act: -0.0000

Data Index: 1157491 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.7541. Min Act: -0.0000

Data Index: 1281693 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1374628 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6435. Min Act: -0.0000

Data Index: 623082 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6071. Min Act: -0.0000

Data Index: 462804 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.6151. Min Act: -0.0000

Data Index: 662155 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 1.9115. Min Range: -1.9115

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1151766 (The Pile)

Max Activating Token Index: 793