Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 383 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5997. Min Act: -0.0004

Data Index: 160069 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6202. Min Act: -0.0004

Data Index: 866551 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5483. Min Act: -0.0004

Data Index: 1280725 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6262. Min Act: -0.0004

Data Index: 333639 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6382. Min Act: -0.0004

Data Index: 193922 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5957. Min Act: -0.0004

Data Index: 1358252 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6069. Min Act: -0.0004

Data Index: 218158 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0004

Data Index: 1078959 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5997. Min Act: -0.0004

Data Index: 45118 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5750. Min Act: -0.0004

Data Index: 929073 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5748. Min Act: -0.0004

Data Index: 480957 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6015. Min Act: -0.0004

Data Index: 517543 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5698. Min Act: -0.0004

Data Index: 972714 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5677. Min Act: -0.0004

Data Index: 942611 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6201. Min Act: -0.0004

Data Index: 455279 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5821. Min Act: -0.0004

Data Index: 143576 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5997. Min Act: -0.0004

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5622. Min Act: -0.0004

Data Index: 447669 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5782. Min Act: -0.0004

Data Index: 1125460 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5748. Min Act: -0.0004

Data Index: 474921 (C4 (Web Text))

Max Activating Token Index: 222