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

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

Neuron 6002 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2916. Min Act: -0.0000

Data Index: 92296 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1657. Min Act: -0.0000

Data Index: 252015 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1711. Min Act: -0.0000

Data Index: 64054 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0007. Min Act: 0.0000

Data Index: 449864 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9191. Min Act: -0.0000

Data Index: 587787 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1034993 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0148. Min Act: -0.0000

Data Index: 743582 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9447. Min Act: -0.0000

Data Index: 958514 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9738. Min Act: -0.0000

Data Index: 609242 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9014. Min Act: -0.0000

Data Index: 8872 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.8352. Min Act: -0.0000

Data Index: 385743 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1189636 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7861. Min Act: -0.0000

Data Index: 780508 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1438554 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7420. Min Act: -0.0000

Data Index: 593993 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7131. Min Act: -0.0000

Data Index: 631663 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.6778. Min Act: -0.0000

Data Index: 603321 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.6595. Min Act: -0.0000

Data Index: 931264 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.7038. Min Act: -0.0000

Data Index: 554227 (C4 (Web Text))

Max Activating Token Index: 598