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

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

Neuron 317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1388620 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1483273 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9515. Min Act: -0.0000

Data Index: 432793 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1479786 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1445913 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1370093 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1371380 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1492964 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1634563 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8873. Min Act: -0.0000

Data Index: 442649 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1338762 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1418097 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1460467 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1431206 (Python Code)

Max Activating Token Index: 567

Text #14

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1587159 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1475944 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1589790 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1425665 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1453472 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1508332 (Python Code)

Max Activating Token Index: 511