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

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

Neuron 1689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4980. Min Act: -0.0000

Data Index: 50791 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.5419. Min Act: -0.0000

Data Index: 373662 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.9706. Min Act: -0.0000

Data Index: 884497 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.0341. Min Act: -0.0000

Data Index: 759384 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7735. Min Act: -0.0000

Data Index: 967851 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8898. Min Act: -0.0000

Data Index: 932578 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.9018. Min Act: -0.0000

Data Index: 39186 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8758. Min Act: -0.0000

Data Index: 610494 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7041. Min Act: -0.0000

Data Index: 1340388 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8364. Min Act: -0.0000

Data Index: 780243 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.9846. Min Act: -0.0000

Data Index: 1321758 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7310. Min Act: -0.0000

Data Index: 761093 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.5464. Min Act: -0.0000

Data Index: 999306 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.6544. Min Act: -0.0000

Data Index: 259948 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.4948. Min Act: -0.0000

Data Index: 1180246 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7680. Min Act: -0.0000

Data Index: 317375 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.6336. Min Act: -0.0000

Data Index: 51262 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.5803. Min Act: -0.0000

Data Index: 614132 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.5307. Min Act: -0.0000

Data Index: 274670 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.6088. Min Act: -0.0000

Data Index: 570101 (C4 (Web Text))

Max Activating Token Index: 954