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

Dataset: The Pile

Neuron 3779 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: 7.4317. Min Range: -7.4317

Max Act: 7.3494. Min Act: -0.0000

Data Index: 1661468 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.2532. Min Act: -0.0000

Data Index: 418336 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.9245. Min Act: -0.0000

Data Index: 1568830 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.1284. Min Act: -0.0000

Data Index: 383369 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.0026. Min Act: -0.0000

Data Index: 1798647 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.9774. Min Act: -0.0000

Data Index: 1110500 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.7596. Min Act: -0.0000

Data Index: 395974 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.1301. Min Act: -0.0000

Data Index: 165487 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.2738. Min Act: -0.0000

Data Index: 1683780 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.7291. Min Act: -0.0000

Data Index: 467672 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.9305. Min Act: -0.0000

Data Index: 1907960 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.7433. Min Act: -0.0000

Data Index: 764214 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.6924. Min Act: -0.0000

Data Index: 1146328 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 7.4317. Min Range: -7.4317

Max Act: 7.4317. Min Act: -0.0000

Data Index: 51145 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.5063. Min Act: -0.0000

Data Index: 665077 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.6532. Min Act: -0.0000

Data Index: 1683647 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.8254. Min Act: -0.0000

Data Index: 1560692 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.8085. Min Act: -0.0000

Data Index: 1697621 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.7860. Min Act: -0.0000

Data Index: 1010172 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 7.4317. Min Range: -7.4317

Max Act: 6.6399. Min Act: -0.0000

Data Index: 911087 (The Pile)

Max Activating Token Index: 914