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

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

Neuron 823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.3193. Min Act: -0.0000

Data Index: 92230 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.1011. Min Act: -0.0000

Data Index: 34001 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.7803. Min Act: -0.0000

Data Index: 524780 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0347. Min Act: -0.0000

Data Index: 91499 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.6555. Min Act: -0.0000

Data Index: 899192 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.4604. Min Act: -0.0000

Data Index: 183293 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1244643 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.5145. Min Act: -0.0000

Data Index: 48334 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.4841. Min Act: -0.0000

Data Index: 60762 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1073277 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.3802. Min Act: -0.0000

Data Index: 915685 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.3678. Min Act: -0.0000

Data Index: 69877 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1214353 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.3038. Min Act: -0.0000

Data Index: 99382 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.0818. Min Act: -0.0001

Data Index: 595428 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.2129. Min Act: -0.0000

Data Index: 561212 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.2213. Min Act: -0.0000

Data Index: 113685 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.2811. Min Act: -0.0000

Data Index: 224590 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.1245. Min Act: -0.0000

Data Index: 392533 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1077685 (C4 (Web Text))

Max Activating Token Index: 92