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

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

Neuron 2941 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0274. Min Range: -2.0274

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1255151 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.7176. Min Act: -0.0000

Data Index: 708096 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.7159. Min Act: -0.0001

Data Index: 309020 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.7146. Min Act: -0.0001

Data Index: 565039 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5820. Min Act: -0.0000

Data Index: 726732 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1084281 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.6676. Min Act: -0.0001

Data Index: 120787 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.6043. Min Act: -0.0001

Data Index: 793499 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4735. Min Act: -0.0000

Data Index: 466141 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.6313. Min Act: -0.0001

Data Index: 417360 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5503. Min Act: -0.0000

Data Index: 902197 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1215899 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5927. Min Act: -0.0001

Data Index: 1035739 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5013. Min Act: -0.0001

Data Index: 204110 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4564. Min Act: -0.0000

Data Index: 448245 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1142466 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4711. Min Act: -0.0001

Data Index: 819347 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4289. Min Act: -0.0000

Data Index: 93964 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4435. Min Act: -0.0001

Data Index: 206579 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 2.0274. Min Range: -2.0274

Max Act: 1.4378. Min Act: -0.0001

Data Index: 206248 (C4 (Web Text))

Max Activating Token Index: 668