Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1073210 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6082. Min Act: -0.0001

Data Index: 4188 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5443. Min Act: -0.0001

Data Index: 386691 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5267. Min Act: -0.0001

Data Index: 881065 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5350. Min Act: -0.0001

Data Index: 794785 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1001939 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5724. Min Act: -0.0001

Data Index: 1266002 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5304. Min Act: -0.0001

Data Index: 25341 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5453. Min Act: -0.0001

Data Index: 22726 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5427. Min Act: -0.0001

Data Index: 242029 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5100. Min Act: -0.0001

Data Index: 2399 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5048. Min Act: -0.0001

Data Index: 375219 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4985. Min Act: -0.0001

Data Index: 833615 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5009. Min Act: -0.0001

Data Index: 776391 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5126. Min Act: -0.0001

Data Index: 813746 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4957. Min Act: -0.0001

Data Index: 414910 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5101. Min Act: -0.0001

Data Index: 708468 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5165. Min Act: -0.0001

Data Index: 753696 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4998. Min Act: -0.0001

Data Index: 881382 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5024. Min Act: -0.0001

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 216