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

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

Neuron 467 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: 0.6318. Min Range: -0.6318

Max Act: 0.5346. Min Act: -0.0000

Data Index: 108184 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1411284 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1640640 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1451714 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1161872 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1449029 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5420. Min Act: -0.0000

Data Index: 385234 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1428971 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6031. Min Act: -0.0000

Data Index: 726058 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1372847 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1574642 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1279940 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1063801 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5351. Min Act: -0.0000

Data Index: 794126 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1381156 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1303458 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4965. Min Act: -0.0000

Data Index: 572902 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1521967 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1224440 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1447312 (Python Code)

Max Activating Token Index: 256