Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5767. Min Act: -0.0000

Data Index: 785582 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5333. Min Act: -0.0001

Data Index: 159458 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5465. Min Act: -0.0001

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4993. Min Act: -0.0001

Data Index: 992911 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5162. Min Act: -0.0001

Data Index: 701488 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5046. Min Act: -0.0000

Data Index: 128198 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4905. Min Act: -0.0001

Data Index: 545141 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4573. Min Act: -0.0001

Data Index: 739943 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4688. Min Act: -0.0001

Data Index: 728225 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1341766 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4781. Min Act: -0.0001

Data Index: 135311 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4412. Min Act: -0.0001

Data Index: 277594 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1920 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4756. Min Act: -0.0001

Data Index: 990179 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4308. Min Act: -0.0001

Data Index: 598479 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4561. Min Act: -0.0001

Data Index: 324865 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4761. Min Act: -0.0001

Data Index: 886334 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3989. Min Act: -0.0001

Data Index: 316185 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4397. Min Act: -0.0001

Data Index: 424251 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4526. Min Act: -0.0001

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 359