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

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

Neuron 244 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8569. Min Act: -0.0003

Data Index: 354134 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8250. Min Act: -0.0002

Data Index: 1134662 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8246. Min Act: -0.0003

Data Index: 1352640 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7802. Min Act: -0.0003

Data Index: 227456 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7846. Min Act: -0.0003

Data Index: 1200931 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7573. Min Act: -0.0003

Data Index: 758570 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7568. Min Act: -0.0002

Data Index: 541585 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7689. Min Act: -0.0003

Data Index: 462281 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7014. Min Act: -0.0003

Data Index: 319267 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7439. Min Act: -0.0002

Data Index: 467375 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6762. Min Act: -0.0003

Data Index: 1038796 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6836. Min Act: -0.0002

Data Index: 1182529 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7064. Min Act: -0.0003

Data Index: 762391 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6883. Min Act: -0.0003

Data Index: 370577 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6786. Min Act: -0.0003

Data Index: 1285412 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6588. Min Act: -0.0003

Data Index: 718004 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6939. Min Act: -0.0003

Data Index: 192593 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6524. Min Act: -0.0002

Data Index: 1240212 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6929. Min Act: -0.0002

Data Index: 590123 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6593. Min Act: -0.0003

Data Index: 8206 (C4 (Web Text))

Max Activating Token Index: 409