Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1170 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0006

Data Index: 21544 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0353. Min Act: -0.0006

Data Index: 609130 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1343083 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0325. Min Act: -0.0006

Data Index: 937126 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0314. Min Act: -0.0006

Data Index: 814275 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0307. Min Act: -0.0006

Data Index: 710893 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1076650 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0305. Min Act: -0.0006

Data Index: 829226 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0313. Min Act: -0.0006

Data Index: 148569 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0320. Min Act: -0.0006

Data Index: 238885 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1250281 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0300. Min Act: -0.0006

Data Index: 980505 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1350914 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0290. Min Act: -0.0006

Data Index: 308840 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0308. Min Act: -0.0006

Data Index: 7282 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0308. Min Act: -0.0006

Data Index: 849835 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0287. Min Act: -0.0006

Data Index: 363133 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0293. Min Act: -0.0006

Data Index: 372444 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1143021 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0292. Min Act: -0.0006

Data Index: 287463 (C4 (Web Text))

Max Activating Token Index: 939