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

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

Neuron 3027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5569. Min Range: -1.5569

Max Act: 1.5569. Min Act: -0.0000

Data Index: 691514 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1337965 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.9538. Min Act: -0.0000

Data Index: 554331 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.8530. Min Act: -0.0000

Data Index: 179664 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.8692. Min Act: -0.0000

Data Index: 921150 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.8486. Min Act: -0.0000

Data Index: 347478 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7563. Min Act: -0.0000

Data Index: 656102 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.8120. Min Act: -0.0000

Data Index: 814453 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7987. Min Act: -0.0000

Data Index: 588418 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7980. Min Act: -0.0000

Data Index: 543885 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1226215 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7455. Min Act: -0.0000

Data Index: 72056 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7396. Min Act: -0.0000

Data Index: 115953 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7657. Min Act: -0.0000

Data Index: 131157 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7565. Min Act: -0.0000

Data Index: 707355 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7286. Min Act: -0.0000

Data Index: 961747 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.6670. Min Act: -0.0000

Data Index: 247217 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.7191. Min Act: -0.0000

Data Index: 916900 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1251837 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.5569. Min Range: -1.5569

Max Act: 0.6971. Min Act: -0.0000

Data Index: 866580 (C4 (Web Text))

Max Activating Token Index: 43