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

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

Neuron 2334 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: 0.8153. Min Range: -0.8153

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1601323 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1618802 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6625. Min Act: -0.0000

Data Index: 940867 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6609. Min Act: -0.0000

Data Index: 165413 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6415. Min Act: -0.0001

Data Index: 1363075 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6035. Min Act: -0.0001

Data Index: 1543736 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1365322 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5805. Min Act: -0.0001

Data Index: 1535340 (Python Code)

Max Activating Token Index: 799

Text #8

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1516002 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1533390 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1594846 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.6082. Min Act: -0.0000

Data Index: 346006 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1448809 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5830. Min Act: -0.0000

Data Index: 247830 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1382252 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5677. Min Act: -0.0001

Data Index: 1548447 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1481363 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1147390 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1538348 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.8153. Min Range: -0.8153

Max Act: 0.5198. Min Act: -0.0000

Data Index: 496664 (C4 (Web Text))

Max Activating Token Index: 663