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

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

Neuron 1860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.2275. Min Act: -0.0001

Data Index: 491539 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8117. Min Act: -0.0001

Data Index: 358476 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.2688. Min Act: -0.0001

Data Index: 105869 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.6883. Min Act: -0.0001

Data Index: 166214 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.4846. Min Act: -0.0001

Data Index: 1005683 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.2853. Min Act: -0.0001

Data Index: 349060 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.2421. Min Act: -0.0001

Data Index: 1193290 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.7463. Min Act: -0.0001

Data Index: 264768 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.4740. Min Act: -0.0001

Data Index: 998268 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.4713. Min Act: -0.0001

Data Index: 849367 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.5566. Min Act: -0.0000

Data Index: 721783 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.3610. Min Act: -0.0000

Data Index: 801015 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.3811. Min Act: -0.0001

Data Index: 846064 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.0741. Min Act: -0.0001

Data Index: 1252930 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.3839. Min Act: -0.0000

Data Index: 630161 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.5142. Min Act: -0.0001

Data Index: 185500 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.5208. Min Act: -0.0001

Data Index: 668077 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.2899. Min Act: -0.0001

Data Index: 977239 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.2876. Min Act: -0.0001

Data Index: 1104907 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 5.2275. Min Range: -5.2275

Max Act: 3.2616. Min Act: -0.0001

Data Index: 916750 (C4 (Web Text))

Max Activating Token Index: 834