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

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

Neuron 2851 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.7152. Min Act: -0.0000

Data Index: 277512 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.5453. Min Act: -0.0000

Data Index: 783979 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.5402. Min Act: -0.0000

Data Index: 689111 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4579. Min Act: -0.0000

Data Index: 809757 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4915. Min Act: -0.0000

Data Index: 440960 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.5041. Min Act: -0.0000

Data Index: 195325 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1091903 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4736. Min Act: -0.0000

Data Index: 52713 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4355. Min Act: -0.0000

Data Index: 655962 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4433. Min Act: -0.0000

Data Index: 141056 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4626. Min Act: -0.0000

Data Index: 517346 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4064. Min Act: -0.0000

Data Index: 278861 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4414. Min Act: -0.0000

Data Index: 134864 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4210. Min Act: -0.0000

Data Index: 648513 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4431. Min Act: -0.0000

Data Index: 892229 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4420. Min Act: -0.0000

Data Index: 908350 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1032973 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4274. Min Act: -0.0000

Data Index: 346065 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1323285 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.7152. Min Range: -0.7152

Max Act: 0.4325. Min Act: -0.0000

Data Index: 321558 (C4 (Web Text))

Max Activating Token Index: 524