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

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

Neuron 299 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1594585 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1615217 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3121. Min Act: -0.0000

Data Index: 873420 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1443589 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1609711 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1510928 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1567244 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1432563 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1418506 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1534931 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1517885 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9905. Min Act: -0.0000

Data Index: 629944 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1302374 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1117441 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0207. Min Act: -0.0000

Data Index: 547836 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1420772 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1461682 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9897. Min Act: -0.0000

Data Index: 167675 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1600741 (Python Code)

Max Activating Token Index: 811

Text #19

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1368869 (Python Code)

Max Activating Token Index: 39