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

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

Neuron 544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.9361. Min Act: -0.0001

Data Index: 510966 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.3990. Min Act: -0.0001

Data Index: 419012 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.4542. Min Act: -0.0001

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.8017. Min Act: -0.0001

Data Index: 382802 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.3091. Min Act: -0.0001

Data Index: 349217 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.8450. Min Act: -0.0001

Data Index: 725006 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.4105. Min Act: -0.0001

Data Index: 1078462 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.2335. Min Act: -0.0001

Data Index: 504902 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.2128. Min Act: -0.0001

Data Index: 814360 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.0182. Min Act: -0.0001

Data Index: 578673 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.7792. Min Act: -0.0001

Data Index: 914946 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.8331. Min Act: -0.0001

Data Index: 90779 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.0697. Min Act: -0.0001

Data Index: 380604 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 3.9361. Min Range: -3.9361

Max Act: 3.0454. Min Act: -0.0001

Data Index: 503081 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.7011. Min Act: -0.0001

Data Index: 1225294 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.9031. Min Act: -0.0001

Data Index: 66223 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.5544. Min Act: -0.0001

Data Index: 1298195 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.9289. Min Act: -0.0001

Data Index: 448473 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.3802. Min Act: -0.0001

Data Index: 1039815 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 3.9361. Min Range: -3.9361

Max Act: 2.4793. Min Act: -0.0001

Data Index: 1010388 (C4 (Web Text))

Max Activating Token Index: 21