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

Dataset: The Pile

Neuron 531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.4677. Min Act: -0.0000

Data Index: 591196 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.3093. Min Act: -0.0000

Data Index: 652149 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1188620 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.3159. Min Act: -0.0000

Data Index: 327388 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.3051. Min Act: -0.0000

Data Index: 763623 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.2961. Min Act: -0.0000

Data Index: 147420 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1937175 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1930030 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.2724. Min Act: -0.0000

Data Index: 575481 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1519132 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1385. Min Act: -0.0000

Data Index: 646100 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1922839 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1365262 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1804441 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1558. Min Act: -0.0000

Data Index: 614160 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1402085 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1366. Min Act: -0.0000

Data Index: 961564 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1972799 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1571315 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1356655 (The Pile)

Max Activating Token Index: 109