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

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

Neuron 4453 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: 3.0259. Min Range: -3.0259

Max Act: 3.0259. Min Act: -0.0000

Data Index: 968881 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 3.0259. Min Range: -3.0259

Max Act: 2.5208. Min Act: -0.0001

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.0259. Min Range: -3.0259

Max Act: 2.4320. Min Act: -0.0000

Data Index: 882470 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.9838. Min Act: -0.0000

Data Index: 784434 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 3.0259. Min Range: -3.0259

Max Act: 2.0263. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1093741 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.7554. Min Act: -0.0000

Data Index: 819464 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.7538. Min Act: -0.0000

Data Index: 1181506 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.7176. Min Act: -0.0000

Data Index: 883258 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.7917. Min Act: -0.0001

Data Index: 110900 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.6816. Min Act: -0.0000

Data Index: 462295 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.6659. Min Act: -0.0000

Data Index: 647929 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.5637. Min Act: -0.0000

Data Index: 497344 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1107957 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1029299 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.7329. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.6084. Min Act: -0.0000

Data Index: 955505 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1331346 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.5808. Min Act: -0.0000

Data Index: 821818 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.0259. Min Range: -3.0259

Max Act: 1.5875. Min Act: -0.0000

Data Index: 342659 (C4 (Web Text))

Max Activating Token Index: 401