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

Dataset: The Pile

Neuron 2672 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: 1.7492. Min Range: -1.7492

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1222361 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1553472 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1573792 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1449547 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1394828 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1615149 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0952. Min Act: -0.0000

Data Index: 222567 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.1069. Min Act: -0.0000

Data Index: 120679 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1167833 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1615818 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0304. Min Act: -0.0000

Data Index: 853974 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0610. Min Act: -0.0000

Data Index: 229544 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0448. Min Act: -0.0000

Data Index: 958365 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0855. Min Act: -0.0000

Data Index: 470290 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1097976 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1447741 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0730. Min Act: -0.0000

Data Index: 87272 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0563. Min Act: -0.0000

Data Index: 361260 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1027322 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.7492. Min Range: -1.7492

Max Act: 1.0442. Min Act: -0.0000

Data Index: 560057 (The Pile)

Max Activating Token Index: 8