Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4690. Min Act: -0.0002

Data Index: 954827 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4131. Min Act: -0.0002

Data Index: 895834 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4187. Min Act: -0.0002

Data Index: 139426 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3854. Min Act: -0.0002

Data Index: 18202 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3913. Min Act: -0.0002

Data Index: 779586 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3847. Min Act: -0.0002

Data Index: 864931 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3714. Min Act: -0.0002

Data Index: 1080297 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3556. Min Act: -0.0002

Data Index: 307734 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3497. Min Act: -0.0002

Data Index: 163628 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3574. Min Act: -0.0002

Data Index: 377776 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3521. Min Act: -0.0002

Data Index: 1215316 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3611. Min Act: -0.0002

Data Index: 912956 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3367. Min Act: -0.0002

Data Index: 413186 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3478. Min Act: -0.0002

Data Index: 903190 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3387. Min Act: -0.0002

Data Index: 577821 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3248. Min Act: -0.0002

Data Index: 1007484 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3240. Min Act: -0.0002

Data Index: 663009 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3249. Min Act: -0.0002

Data Index: 428086 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3336. Min Act: -0.0002

Data Index: 1256696 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3214. Min Act: -0.0002

Data Index: 988421 (C4 (Web Text))

Max Activating Token Index: 19