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

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

Neuron 5044 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: 0.8195. Min Range: -0.8195

Max Act: 0.8195. Min Act: -0.0000

Data Index: 894455 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.8069. Min Act: -0.0000

Data Index: 580865 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1094877 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6547. Min Act: -0.0000

Data Index: 243805 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6880. Min Act: -0.0000

Data Index: 789876 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1173758 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6079. Min Act: -0.0000

Data Index: 495150 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1028636 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5581. Min Act: -0.0000

Data Index: 173033 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5932. Min Act: -0.0000

Data Index: 271476 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1261014 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5653. Min Act: -0.0000

Data Index: 79499 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5411. Min Act: -0.0000

Data Index: 454680 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5080. Min Act: -0.0000

Data Index: 54656 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1277480 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.4445. Min Act: -0.0000

Data Index: 497003 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5155. Min Act: -0.0000

Data Index: 640810 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.4877. Min Act: -0.0000

Data Index: 399539 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.4491. Min Act: -0.0000

Data Index: 268204 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1199956 (C4 (Web Text))

Max Activating Token Index: 239