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

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

Neuron 487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6155. Min Range: -7.6155

Max Act: 7.6155. Min Act: -0.0000

Data Index: 1397648 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 7.6155. Min Range: -7.6155

Max Act: 7.4518. Min Act: -0.0001

Data Index: 1558923 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.9690. Min Act: -0.0000

Data Index: 1540894 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.6743. Min Act: -0.0001

Data Index: 1491638 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.7684. Min Act: -0.0001

Data Index: 1409418 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.9681. Min Act: -0.0001

Data Index: 1645439 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.6761. Min Act: -0.0001

Data Index: 1618245 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.4812. Min Act: -0.0001

Data Index: 1389696 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.4751. Min Act: -0.0001

Data Index: 1435049 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.4659. Min Act: -0.0000

Data Index: 1644105 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.3602. Min Act: -0.0001

Data Index: 1393856 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.1360. Min Act: -0.0001

Data Index: 1490522 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.4411. Min Act: -0.0001

Data Index: 1617145 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.0277. Min Act: -0.0001

Data Index: 1458265 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.7326. Min Act: -0.0001

Data Index: 1650903 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.2015. Min Act: -0.0000

Data Index: 1558748 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.0018. Min Act: -0.0001

Data Index: 1565706 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 7.6155. Min Range: -7.6155

Max Act: 5.6190. Min Act: -0.0001

Data Index: 1474145 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 7.6155. Min Range: -7.6155

Max Act: 6.3372. Min Act: -0.0001

Data Index: 1624745 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 7.6155. Min Range: -7.6155

Max Act: 5.7365. Min Act: -0.0001

Data Index: 1573148 (Python Code)

Max Activating Token Index: 265