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

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

Neuron 1339 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.4978. Min Act: -0.0001

Data Index: 1338831 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3965. Min Act: -0.0001

Data Index: 961289 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3289. Min Act: -0.0001

Data Index: 1073585 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.5116. Min Act: -0.0001

Data Index: 21341 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2285. Min Act: -0.0001

Data Index: 335411 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.3418. Min Act: -0.0001

Data Index: 483904 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2377. Min Act: -0.0001

Data Index: 1075329 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2587. Min Act: -0.0001

Data Index: 42227 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.4404. Min Act: -0.0001

Data Index: 647642 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1051. Min Act: -0.0001

Data Index: 900881 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.2252. Min Act: -0.0001

Data Index: 86986 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1918. Min Act: -0.0001

Data Index: 520133 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1460. Min Act: -0.0001

Data Index: 1183013 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1000. Min Act: -0.0001

Data Index: 670998 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0265. Min Act: -0.0001

Data Index: 661596 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.1879. Min Act: -0.0001

Data Index: 199468 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0359. Min Act: -0.0001

Data Index: 803933 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0395. Min Act: -0.0001

Data Index: 681667 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0319. Min Act: -0.0001

Data Index: 95666 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.5116. Min Range: -1.5116

Max Act: 1.0633. Min Act: -0.0001

Data Index: 428734 (C4 (Web Text))

Max Activating Token Index: 9