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

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

Neuron 5042 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: 2.9013. Min Range: -2.9013

Max Act: 2.7868. Min Act: -0.0000

Data Index: 395216 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.9013. Min Act: -0.0000

Data Index: 999272 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.5504. Min Act: -0.0001

Data Index: 884247 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.5266. Min Act: -0.0001

Data Index: 735687 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.7514. Min Act: -0.0000

Data Index: 650418 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.5289. Min Act: -0.0001

Data Index: 887439 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.4867. Min Act: -0.0000

Data Index: 1137048 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.6093. Min Act: -0.0001

Data Index: 30490 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.4788. Min Act: -0.0001

Data Index: 70013 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.5993. Min Act: -0.0000

Data Index: 1054675 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.4068. Min Act: -0.0000

Data Index: 950757 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.4084. Min Act: -0.0001

Data Index: 1324645 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.2281. Min Act: -0.0001

Data Index: 1285757 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.3123. Min Act: -0.0000

Data Index: 444055 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.1499. Min Act: -0.0001

Data Index: 904113 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1265098 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.5572. Min Act: -0.0000

Data Index: 728484 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.3567. Min Act: -0.0000

Data Index: 271456 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.2185. Min Act: -0.0001

Data Index: 521412 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 2.9013. Min Range: -2.9013

Max Act: 2.0903. Min Act: -0.0000

Data Index: 1184761 (C4 (Web Text))

Max Activating Token Index: 759