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

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

Neuron 3598 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.8188. Min Act: -0.0000

Data Index: 870739 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.6280. Min Act: -0.0000

Data Index: 465303 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.2024. Min Act: -0.0000

Data Index: 1032664 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.3209. Min Act: -0.0000

Data Index: 489093 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.2741. Min Act: -0.0000

Data Index: 559819 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.1299. Min Act: -0.0000

Data Index: 742208 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.1126. Min Act: -0.0000

Data Index: 51681 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.7717. Min Act: -0.0000

Data Index: 1462450 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.0634. Min Act: -0.0000

Data Index: 288051 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1323482 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.6841. Min Act: -0.0000

Data Index: 241737 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.8508. Min Act: -0.0000

Data Index: 464168 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.7989. Min Act: -0.0000

Data Index: 353192 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.8188. Min Range: -2.8188

Max Act: 2.0287. Min Act: -0.0000

Data Index: 195841 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.9927. Min Act: -0.0000

Data Index: 127816 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.8813. Min Act: -0.0000

Data Index: 808902 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.7244. Min Act: -0.0000

Data Index: 573565 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.8703. Min Act: -0.0000

Data Index: 1211673 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.7538. Min Act: -0.0000

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.8188. Min Range: -2.8188

Max Act: 1.7450. Min Act: -0.0000

Data Index: 174258 (C4 (Web Text))

Max Activating Token Index: 857