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

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

Neuron 1450 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5790. Min Range: -3.5790

Max Act: 3.5790. Min Act: -0.0000

Data Index: 1015859 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.5790. Min Range: -3.5790

Max Act: 3.3092. Min Act: -0.0000

Data Index: 1212758 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 3.5790. Min Range: -3.5790

Max Act: 3.1048. Min Act: -0.0000

Data Index: 242824 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.5790. Min Range: -3.5790

Max Act: 3.0580. Min Act: -0.0001

Data Index: 64846 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.9002. Min Act: -0.0000

Data Index: 760753 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.9102. Min Act: -0.0000

Data Index: 570425 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.6398. Min Act: -0.0000

Data Index: 516323 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.8057. Min Act: -0.0000

Data Index: 550842 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.7628. Min Act: -0.0000

Data Index: 996021 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.5981. Min Act: -0.0000

Data Index: 428698 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.6698. Min Act: -0.0000

Data Index: 642698 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.5230. Min Act: -0.0000

Data Index: 120293 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.4473. Min Act: -0.0000

Data Index: 836583 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.9556. Min Act: -0.0000

Data Index: 167484 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.4300. Min Act: -0.0000

Data Index: 370830 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.3333. Min Act: -0.0000

Data Index: 974920 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.2157. Min Act: -0.0000

Data Index: 1014810 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.4245. Min Act: -0.0001

Data Index: 1020716 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.2613. Min Act: -0.0000

Data Index: 389769 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 3.5790. Min Range: -3.5790

Max Act: 2.5048. Min Act: -0.0000

Data Index: 171894 (C4 (Web Text))

Max Activating Token Index: 567