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

Dataset: The Pile

Neuron 3660 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.9120. Min Act: -0.0000

Data Index: 1063176 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.8362. Min Act: -0.0000

Data Index: 1213507 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.9406. Min Act: -0.0000

Data Index: 1719889 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3900. Min Act: -0.0000

Data Index: 1333256 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1081471 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.2320. Min Act: -0.0000

Data Index: 869860 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.1397. Min Act: -0.0000

Data Index: 503245 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.8881. Min Act: -0.0000

Data Index: 34032 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.7407. Min Act: -0.0000

Data Index: 1073261 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.7223. Min Act: -0.0000

Data Index: 1251548 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.7839. Min Act: -0.0000

Data Index: 1812794 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.0663. Min Act: -0.0000

Data Index: 309394 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.6135. Min Act: -0.0000

Data Index: 185665 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.7038. Min Act: -0.0000

Data Index: 1553752 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.8859. Min Act: -0.0000

Data Index: 1731831 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.6778. Min Act: -0.0000

Data Index: 340164 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.3808. Min Act: -0.0000

Data Index: 490317 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.6581. Min Act: -0.0000

Data Index: 1245895 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.6032. Min Act: -0.0000

Data Index: 1508528 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 3.9406. Min Range: -3.9406

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1134305 (The Pile)

Max Activating Token Index: 121