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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.4695. Min Act: -0.0001

Data Index: 601591 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.5297. Min Act: -0.0001

Data Index: 156056 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1184927 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.3648. Min Act: -0.0001

Data Index: 1140987 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1278. Min Act: -0.0001

Data Index: 463005 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1878. Min Act: -0.0001

Data Index: 811960 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2431. Min Act: -0.0001

Data Index: 573804 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1618. Min Act: -0.0001

Data Index: 260050 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1728. Min Act: -0.0001

Data Index: 725764 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1229. Min Act: -0.0001

Data Index: 1178980 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2127. Min Act: -0.0001

Data Index: 1118771 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2168. Min Act: -0.0001

Data Index: 753836 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1691. Min Act: -0.0001

Data Index: 1276965 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1016841 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0076. Min Act: -0.0001

Data Index: 388097 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0215. Min Act: -0.0001

Data Index: 955280 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.8957. Min Act: -0.0001

Data Index: 815665 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0832. Min Act: -0.0001

Data Index: 836947 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0821. Min Act: -0.0001

Data Index: 513109 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9970. Min Act: -0.0001

Data Index: 360090 (C4 (Web Text))

Max Activating Token Index: 295