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

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

Neuron 4326 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.2325. Min Act: -0.0000

Data Index: 870456 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0648. Min Act: -0.0000

Data Index: 716444 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9678. Min Act: 0.0000

Data Index: 984182 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0229. Min Act: -0.0000

Data Index: 635940 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1006881 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9896. Min Act: -0.0000

Data Index: 843045 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9911. Min Act: -0.0000

Data Index: 919759 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9850. Min Act: -0.0000

Data Index: 957104 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9735. Min Act: -0.0000

Data Index: 506695 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9692. Min Act: -0.0000

Data Index: 363297 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9379. Min Act: -0.0000

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9046. Min Act: -0.0000

Data Index: 424235 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9462. Min Act: -0.0000

Data Index: 444311 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9257. Min Act: -0.0000

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8975. Min Act: -0.0000

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8732. Min Act: -0.0000

Data Index: 635703 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1138386 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8595. Min Act: -0.0000

Data Index: 960491 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8417. Min Act: -0.0000

Data Index: 811691 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8619. Min Act: -0.0000

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 511