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

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

Neuron 3163 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: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0000

Data Index: 117403 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1284892 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1098. Min Act: -0.0000

Data Index: 183877 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1166. Min Act: -0.0000

Data Index: 556776 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1061252 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0932. Min Act: -0.0000

Data Index: 995957 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0842. Min Act: -0.0000

Data Index: 997200 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0872. Min Act: -0.0000

Data Index: 6890 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0871. Min Act: -0.0001

Data Index: 742629 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0863. Min Act: -0.0001

Data Index: 168043 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0757. Min Act: -0.0001

Data Index: 419838 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0774. Min Act: -0.0000

Data Index: 548514 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0861. Min Act: -0.0000

Data Index: 731254 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0802. Min Act: -0.0000

Data Index: 522927 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1219312 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0797. Min Act: -0.0000

Data Index: 574084 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1305334 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1596814 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1119983 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0749. Min Act: -0.0001

Data Index: 718973 (C4 (Web Text))

Max Activating Token Index: 228