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

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

Neuron 1261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.4133. Min Act: -0.0001

Data Index: 738316 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.2353. Min Act: -0.0001

Data Index: 634514 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.1361. Min Act: -0.0001

Data Index: 90940 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.2172. Min Act: -0.0001

Data Index: 742848 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0821. Min Act: -0.0001

Data Index: 104496 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0382. Min Act: -0.0001

Data Index: 11875 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0227. Min Act: -0.0001

Data Index: 211358 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.1094. Min Act: -0.0001

Data Index: 255576 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0201. Min Act: -0.0000

Data Index: 622776 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0073. Min Act: -0.0001

Data Index: 342218 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0015. Min Act: -0.0000

Data Index: 154962 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.4133. Min Range: -1.4133

Max Act: 0.9725. Min Act: -0.0001

Data Index: 654738 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0180. Min Act: -0.0001

Data Index: 260542 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0199. Min Act: -0.0001

Data Index: 764552 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.4133. Min Range: -1.4133

Max Act: 0.9811. Min Act: -0.0001

Data Index: 790625 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0253. Min Act: -0.0001

Data Index: 360457 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.4133. Min Range: -1.4133

Max Act: 1.0013. Min Act: -0.0001

Data Index: 455943 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.4133. Min Range: -1.4133

Max Act: 0.9689. Min Act: -0.0001

Data Index: 937029 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.4133. Min Range: -1.4133

Max Act: 0.9267. Min Act: -0.0000

Data Index: 499445 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.4133. Min Range: -1.4133

Max Act: 0.8837. Min Act: -0.0000

Data Index: 703313 (C4 (Web Text))

Max Activating Token Index: 253