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

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

Neuron 664 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: 0.6032. Min Range: -0.6032

Max Act: 0.5982. Min Act: -0.0001

Data Index: 1221348 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5495. Min Act: -0.0001

Data Index: 940869 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.6032. Min Act: -0.0001

Data Index: 881944 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5383. Min Act: -0.0001

Data Index: 263716 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5121. Min Act: -0.0001

Data Index: 823062 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5273. Min Act: -0.0001

Data Index: 295179 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5054. Min Act: -0.0001

Data Index: 120860 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5370. Min Act: -0.0001

Data Index: 804968 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5377. Min Act: -0.0001

Data Index: 1315131 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5042. Min Act: -0.0001

Data Index: 731401 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5111. Min Act: -0.0001

Data Index: 817781 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5074. Min Act: -0.0001

Data Index: 525382 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4749. Min Act: -0.0001

Data Index: 239894 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1183597 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4711. Min Act: -0.0001

Data Index: 417272 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5308. Min Act: -0.0001

Data Index: 100809 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4796. Min Act: -0.0001

Data Index: 588870 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4725. Min Act: -0.0001

Data Index: 495411 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1013101 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4647. Min Act: -0.0001

Data Index: 667205 (C4 (Web Text))

Max Activating Token Index: 706