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

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

Neuron 3434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9961. Min Act: -0.0000

Data Index: 518573 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0238. Min Act: -0.0001

Data Index: 799397 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1088481 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9751. Min Act: -0.0000

Data Index: 27373 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1196708 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9373. Min Act: -0.0001

Data Index: 1160143 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9381. Min Act: -0.0000

Data Index: 212409 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9092. Min Act: -0.0000

Data Index: 380995 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9176. Min Act: -0.0001

Data Index: 478290 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1003222 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8951. Min Act: -0.0001

Data Index: 253745 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1078751 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8698. Min Act: -0.0001

Data Index: 366730 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1014601 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1335254 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8482. Min Act: -0.0001

Data Index: 173083 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1157674 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8409. Min Act: -0.0001

Data Index: 1092725 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8423. Min Act: -0.0000

Data Index: 360082 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1012651 (C4 (Web Text))

Max Activating Token Index: 962