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

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

Neuron 5085 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1392514 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.1249. Min Act: -0.0000

Data Index: 141742 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.9880. Min Act: -0.0000

Data Index: 855532 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1408878 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.0727. Min Act: -0.0000

Data Index: 474006 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.0217. Min Act: -0.0000

Data Index: 937087 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8870. Min Act: -0.0000

Data Index: 34264 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.0445. Min Act: -0.0000

Data Index: 453861 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.9257. Min Act: -0.0000

Data Index: 528072 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8280. Min Act: -0.0000

Data Index: 629467 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.9246. Min Act: -0.0000

Data Index: 734269 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8670. Min Act: -0.0000

Data Index: 974987 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8323. Min Act: -0.0000

Data Index: 567760 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8225. Min Act: -0.0000

Data Index: 716128 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1231301 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8282. Min Act: -0.0000

Data Index: 705734 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1564102 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1424516 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8298. Min Act: -0.0000

Data Index: 17612 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1435263 (Python Code)

Max Activating Token Index: 302