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

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

Neuron 3928 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: 1.8050. Min Range: -1.8050

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1393339 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1585634 (Python Code)

Max Activating Token Index: 750

Text #2

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1480044 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.6981. Min Act: -0.0000

Data Index: 1389713 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1366112 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1640312 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1516109 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1588294 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1377882 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1602896 (Python Code)

Max Activating Token Index: 482

Text #10

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1532595 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1645707 (Python Code)

Max Activating Token Index: 939

Text #12

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1459386 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1493038 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1606207 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1448328 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1515844 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1436985 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1466691 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1415693 (Python Code)

Max Activating Token Index: 866