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

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

Neuron 3455 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: 0.6525. Min Range: -0.6525

Max Act: 0.6525. Min Act: -0.0001

Data Index: 783378 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.6149. Min Act: -0.0001

Data Index: 1023149 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5757. Min Act: -0.0001

Data Index: 819750 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5451. Min Act: -0.0001

Data Index: 655490 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1069366 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5319. Min Act: -0.0001

Data Index: 469781 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5233. Min Act: -0.0001

Data Index: 184470 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5193. Min Act: -0.0001

Data Index: 134077 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5158. Min Act: -0.0001

Data Index: 161187 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4626. Min Act: -0.0001

Data Index: 580763 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5243. Min Act: -0.0001

Data Index: 969660 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5001. Min Act: -0.0001

Data Index: 125166 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5006. Min Act: -0.0001

Data Index: 388793 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5007. Min Act: -0.0001

Data Index: 303048 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4995. Min Act: -0.0001

Data Index: 602063 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5166. Min Act: -0.0001

Data Index: 318727 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4898. Min Act: -0.0001

Data Index: 92740 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4757. Min Act: -0.0001

Data Index: 277201 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5095. Min Act: -0.0001

Data Index: 501563 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4741. Min Act: -0.0001

Data Index: 571041 (C4 (Web Text))

Max Activating Token Index: 93