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

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

Neuron 3200 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: 0.7160. Min Range: -0.7160

Max Act: 0.7160. Min Act: -0.0001

Data Index: 902837 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6852. Min Act: -0.0001

Data Index: 342761 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6492. Min Act: -0.0001

Data Index: 157667 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5869. Min Act: -0.0001

Data Index: 724510 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6403. Min Act: -0.0001

Data Index: 245813 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6227. Min Act: -0.0001

Data Index: 748759 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6327. Min Act: -0.0001

Data Index: 1320820 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6468. Min Act: -0.0001

Data Index: 907893 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1024299 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6431. Min Act: -0.0001

Data Index: 468661 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5969. Min Act: -0.0001

Data Index: 404191 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6146. Min Act: -0.0001

Data Index: 636013 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1092907 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1324220 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6024. Min Act: -0.0001

Data Index: 543124 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5774. Min Act: -0.0001

Data Index: 454065 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5386. Min Act: -0.0001

Data Index: 40847 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.6149. Min Act: -0.0001

Data Index: 953323 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5709. Min Act: -0.0001

Data Index: 63682 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.7160. Min Range: -0.7160

Max Act: 0.5296. Min Act: -0.0001

Data Index: 1239404 (C4 (Web Text))

Max Activating Token Index: 625