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

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

Neuron 1879 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: 0.7299. Min Range: -0.7299

Max Act: 0.6985. Min Act: -0.0000

Data Index: 235219 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.7299. Min Act: -0.0000

Data Index: 505069 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6623. Min Act: -0.0000

Data Index: 380264 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6635. Min Act: -0.0001

Data Index: 506103 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5991. Min Act: -0.0000

Data Index: 527955 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5455. Min Act: -0.0000

Data Index: 749057 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1245998 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5023. Min Act: -0.0000

Data Index: 8910 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1026734 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5274. Min Act: -0.0000

Data Index: 980081 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5211. Min Act: -0.0000

Data Index: 578736 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5308. Min Act: -0.0000

Data Index: 868376 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5101. Min Act: -0.0000

Data Index: 5572 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1202381 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5068. Min Act: -0.0000

Data Index: 16306 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4982. Min Act: -0.0000

Data Index: 413325 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1272362 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1343092 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4777. Min Act: -0.0000

Data Index: 463141 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4479. Min Act: -0.0001

Data Index: 215177 (C4 (Web Text))

Max Activating Token Index: 795