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

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

Neuron 200 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: 1.0294. Min Range: -1.0294

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1181264 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8860. Min Act: -0.0001

Data Index: 1316382 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9098. Min Act: -0.0000

Data Index: 865623 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8503. Min Act: -0.0000

Data Index: 520500 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1156696 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9742. Min Act: -0.0000

Data Index: 757680 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8563. Min Act: -0.0000

Data Index: 89523 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8422. Min Act: -0.0000

Data Index: 94303 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7872. Min Act: -0.0001

Data Index: 473799 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1191519 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8583. Min Act: -0.0000

Data Index: 119126 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1308175 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8536. Min Act: -0.0000

Data Index: 491828 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8147. Min Act: -0.0000

Data Index: 715007 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8336. Min Act: -0.0000

Data Index: 238111 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1344367 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1323940 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1305795 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8153. Min Act: -0.0000

Data Index: 908447 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7906. Min Act: -0.0000

Data Index: 409532 (C4 (Web Text))

Max Activating Token Index: 439