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

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

Neuron 507 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7243. Min Range: -3.7243

Max Act: 3.5922. Min Act: -0.0000

Data Index: 660661 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 3.7243. Min Range: -3.7243

Max Act: 3.7243. Min Act: -0.0000

Data Index: 655750 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.8240. Min Act: -0.0000

Data Index: 924358 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.7347. Min Act: -0.0000

Data Index: 244366 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.7888. Min Act: -0.0000

Data Index: 993044 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.5115. Min Act: -0.0000

Data Index: 1314380 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.8529. Min Act: -0.0000

Data Index: 972731 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.2846. Min Act: -0.0000

Data Index: 751028 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.5170. Min Act: -0.0000

Data Index: 857318 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.3004. Min Act: -0.0000

Data Index: 995327 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.5025. Min Act: -0.0000

Data Index: 56804 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.3390. Min Act: -0.0000

Data Index: 8461 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.6779. Min Act: -0.0000

Data Index: 1066757 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.3060. Min Act: -0.0000

Data Index: 1291035 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.0468. Min Act: -0.0000

Data Index: 345214 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.1346. Min Act: -0.0000

Data Index: 444680 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.4319. Min Act: -0.0000

Data Index: 529306 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.1782. Min Act: -0.0000

Data Index: 1321774 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.0371. Min Act: -0.0000

Data Index: 573979 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 3.7243. Min Range: -3.7243

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1235717 (C4 (Web Text))

Max Activating Token Index: 533