Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1860 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6637. Min Act: -0.0006

Data Index: 516916 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6211. Min Act: -0.0006

Data Index: 1244047 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6115. Min Act: -0.0006

Data Index: 1070867 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6195. Min Act: -0.0006

Data Index: 1283243 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5934. Min Act: -0.0006

Data Index: 1019578 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5148. Min Act: -0.0006

Data Index: 821808 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5894. Min Act: -0.0006

Data Index: 1110343 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5931. Min Act: -0.0006

Data Index: 720778 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6058. Min Act: -0.0006

Data Index: 274544 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5809. Min Act: -0.0006

Data Index: 883082 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5772. Min Act: -0.0006

Data Index: 238252 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5778. Min Act: -0.0006

Data Index: 283302 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6112. Min Act: -0.0006

Data Index: 863911 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6309. Min Act: -0.0006

Data Index: 696366 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5496. Min Act: -0.0006

Data Index: 696965 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5643. Min Act: -0.0006

Data Index: 980532 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5282. Min Act: -0.0006

Data Index: 1105552 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6052. Min Act: -0.0006

Data Index: 800050 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5205. Min Act: -0.0006

Data Index: 559826 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6398. Min Act: -0.0006

Data Index: 72426 (C4 (Web Text))

Max Activating Token Index: 938