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

Dataset: The Pile

Neuron 2263 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1307752 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3040. Min Act: -0.0000

Data Index: 942809 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2834. Min Act: -0.0000

Data Index: 923015 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1523205 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1232525 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1076273 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1705536 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1338135 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2463. Min Act: -0.0000

Data Index: 580370 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2703. Min Act: -0.0000

Data Index: 259794 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1961922 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2619. Min Act: -0.0000

Data Index: 583086 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2358. Min Act: -0.0000

Data Index: 594582 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2379. Min Act: -0.0000

Data Index: 83898 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2206. Min Act: -0.0000

Data Index: 100530 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2212. Min Act: -0.0000

Data Index: 850223 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2204. Min Act: -0.0000

Data Index: 539057 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1506106 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2194. Min Act: -0.0000

Data Index: 238378 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2356. Min Act: -0.0001

Data Index: 797632 (The Pile)

Max Activating Token Index: 953