Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.6410. Min Act: -0.0000

Data Index: 271741 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.6200. Min Act: -0.0000

Data Index: 693582 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.6179. Min Act: -0.0001

Data Index: 820156 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.5753. Min Act: -0.0000

Data Index: 280965 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.5516. Min Act: -0.0001

Data Index: 750734 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.5531. Min Act: -0.0000

Data Index: 730015 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.5418. Min Act: -0.0000

Data Index: 330393 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4842. Min Act: -0.0000

Data Index: 729247 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1146933 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1321878 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1224645 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4675. Min Act: -0.0000

Data Index: 345918 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4737. Min Act: -0.0000

Data Index: 351005 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1039403 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1162867 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4488. Min Act: -0.0000

Data Index: 824173 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4774. Min Act: -0.0000

Data Index: 536790 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4580. Min Act: -0.0000

Data Index: 4347 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4705. Min Act: -0.0001

Data Index: 934240 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.6410. Min Range: -0.6410

Max Act: 0.4547. Min Act: -0.0000

Data Index: 299080 (C4 (Web Text))

Max Activating Token Index: 370