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

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

Neuron 924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9271. Min Act: -0.0002

Data Index: 1506950 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9842. Min Act: -0.0002

Data Index: 1555466 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9077. Min Act: -0.0002

Data Index: 1452922 (Python Code)

Max Activating Token Index: 703

Text #3

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.7824. Min Act: -0.0002

Data Index: 1624681 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9559. Min Act: -0.0002

Data Index: 1517617 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9476. Min Act: -0.0002

Data Index: 1469942 (Python Code)

Max Activating Token Index: 427

Text #6

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8167. Min Act: -0.0002

Data Index: 1490869 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9341. Min Act: -0.0002

Data Index: 1643665 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9756. Min Act: -0.0002

Data Index: 1648772 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9168. Min Act: -0.0002

Data Index: 1398296 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8831. Min Act: -0.0002

Data Index: 1630838 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8533. Min Act: -0.0002

Data Index: 1656654 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.9098. Min Act: -0.0002

Data Index: 1567191 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8794. Min Act: -0.0002

Data Index: 1615220 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.7367. Min Act: -0.0002

Data Index: 1427499 (Python Code)

Max Activating Token Index: 757

Text #15

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8009. Min Act: -0.0002

Data Index: 1565868 (Python Code)

Max Activating Token Index: 670

Text #16

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.7798. Min Act: -0.0002

Data Index: 1444525 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8979. Min Act: -0.0002

Data Index: 1527932 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.8698. Min Act: -0.0002

Data Index: 1616638 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 0.9842. Min Range: -0.9842

Max Act: 0.7994. Min Act: -0.0002

Data Index: 1565489 (Python Code)

Max Activating Token Index: 104