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

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

Neuron 4816 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1327. Min Range: -1.1327

Max Act: 1.1327. Min Act: -0.0000

Data Index: 50368 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8878. Min Act: -0.0000

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8997. Min Act: -0.0000

Data Index: 281493 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8431. Min Act: -0.0000

Data Index: 116580 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8007. Min Act: -0.0000

Data Index: 606993 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7480. Min Act: -0.0000

Data Index: 464860 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7692. Min Act: -0.0000

Data Index: 462198 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7663. Min Act: -0.0000

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.8063. Min Act: -0.0000

Data Index: 432459 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7961. Min Act: -0.0000

Data Index: 382670 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7192. Min Act: -0.0000

Data Index: 371849 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7404. Min Act: -0.0000

Data Index: 627646 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.7175. Min Act: -0.0000

Data Index: 82328 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1231244 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6675. Min Act: -0.0000

Data Index: 798555 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1081515 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6603. Min Act: -0.0000

Data Index: 852811 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6423. Min Act: -0.0000

Data Index: 327366 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6503. Min Act: -0.0000

Data Index: 231336 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.1327. Min Range: -1.1327

Max Act: 0.6245. Min Act: -0.0000

Data Index: 951867 (C4 (Web Text))

Max Activating Token Index: 750