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

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

Neuron 2792 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1575005 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.2650. Min Act: 0.0000

Data Index: 1488892 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1494514 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1485117 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1475728 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1606682 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1379420 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 1.2651. Min Range: -1.2651

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1648701 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1450364 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1479602 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1471092 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1492405 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1566527 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1614337 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1596361 (Python Code)

Max Activating Token Index: 515

Text #15

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1516508 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1552971 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1599961 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1649092 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 1.2651. Min Range: -1.2651

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1388033 (Python Code)

Max Activating Token Index: 1008