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

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

Neuron 756 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: 1.2521. Min Range: -1.2521

Max Act: 1.2521. Min Act: -0.0000

Data Index: 264 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.1786. Min Act: -0.0000

Data Index: 610316 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.0914. Min Act: -0.0000

Data Index: 286610 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.1864. Min Act: -0.0000

Data Index: 739639 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.0668. Min Act: -0.0000

Data Index: 466236 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.0668. Min Act: -0.0000

Data Index: 414607 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.2521. Min Range: -1.2521

Max Act: 1.0565. Min Act: -0.0000

Data Index: 416350 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9651. Min Act: -0.0000

Data Index: 88985 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1117046 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9348. Min Act: -0.0000

Data Index: 523 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9265. Min Act: -0.0000

Data Index: 9732 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1157224 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9260. Min Act: -0.0000

Data Index: 506676 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1136880 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.9196. Min Act: -0.0000

Data Index: 428657 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8284. Min Act: -0.0000

Data Index: 88087 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8556. Min Act: -0.0000

Data Index: 962627 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8482. Min Act: -0.0000

Data Index: 889605 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8954. Min Act: -0.0000

Data Index: 718350 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.2521. Min Range: -1.2521

Max Act: 0.8753. Min Act: -0.0000

Data Index: 285315 (C4 (Web Text))

Max Activating Token Index: 461