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

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

Neuron 3425 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2570. Min Act: -0.0001

Data Index: 995503 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1089060 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1011551 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1986. Min Act: -0.0001

Data Index: 649397 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2063. Min Act: -0.0001

Data Index: 246145 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2038. Min Act: -0.0001

Data Index: 335124 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2157. Min Act: -0.0001

Data Index: 720232 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1859. Min Act: -0.0001

Data Index: 695593 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2040. Min Act: -0.0001

Data Index: 722757 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1751. Min Act: -0.0001

Data Index: 725274 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1924. Min Act: -0.0001

Data Index: 604770 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1723. Min Act: -0.0001

Data Index: 823649 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1697. Min Act: -0.0001

Data Index: 31167 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1597. Min Act: -0.0001

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1951. Min Act: -0.0001

Data Index: 361078 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1799. Min Act: -0.0001

Data Index: 387542 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1824. Min Act: -0.0001

Data Index: 335739 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1665. Min Act: -0.0001

Data Index: 774636 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1525. Min Act: -0.0001

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1557. Min Act: -0.0001

Data Index: 947258 (C4 (Web Text))

Max Activating Token Index: 695