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

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

Neuron 2140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1206282 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7913. Min Act: -0.0000

Data Index: 919977 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7785. Min Act: -0.0000

Data Index: 56326 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1339060 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6925. Min Act: -0.0000

Data Index: 241092 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7221. Min Act: -0.0000

Data Index: 955432 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1160568 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6527. Min Act: -0.0000

Data Index: 719158 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7065. Min Act: -0.0000

Data Index: 915572 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6625. Min Act: -0.0000

Data Index: 749552 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1272371 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7025. Min Act: -0.0000

Data Index: 677288 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6556. Min Act: -0.0000

Data Index: 917281 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1063062 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6674. Min Act: -0.0000

Data Index: 619859 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1433067 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6381. Min Act: -0.0000

Data Index: 694959 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6609. Min Act: -0.0000

Data Index: 964231 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1324855 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6404. Min Act: -0.0000

Data Index: 599500 (C4 (Web Text))

Max Activating Token Index: 73