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

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

Neuron 1970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1056373 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1989. Min Act: -0.0001

Data Index: 17651 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1873. Min Act: -0.0001

Data Index: 641709 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1104795 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1964. Min Act: -0.0001

Data Index: 379368 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1793. Min Act: -0.0001

Data Index: 147536 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1247992 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1835. Min Act: -0.0001

Data Index: 406205 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1884. Min Act: -0.0001

Data Index: 526414 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1866. Min Act: -0.0001

Data Index: 353670 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1728. Min Act: -0.0001

Data Index: 490480 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1787. Min Act: -0.0001

Data Index: 316571 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1760. Min Act: -0.0001

Data Index: 558337 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1760. Min Act: -0.0001

Data Index: 835752 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1760. Min Act: -0.0001

Data Index: 716480 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1760. Min Act: -0.0001

Data Index: 293318 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1776. Min Act: -0.0001

Data Index: 848359 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1762. Min Act: -0.0001

Data Index: 479228 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1761. Min Act: -0.0001

Data Index: 641658 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.2154. Min Range: -0.2154

Max Act: 0.1773. Min Act: -0.0001

Data Index: 756792 (C4 (Web Text))

Max Activating Token Index: 177