Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3444. Min Act: -0.0001

Data Index: 85256 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3618. Min Act: -0.0001

Data Index: 843490 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3288. Min Act: -0.0001

Data Index: 715860 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1152934 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1303313 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2697. Min Act: -0.0001

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1117359 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2564. Min Act: -0.0001

Data Index: 460738 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2364. Min Act: -0.0001

Data Index: 453914 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2440. Min Act: -0.0001

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2344. Min Act: -0.0001

Data Index: 342453 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1162685 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2171. Min Act: -0.0001

Data Index: 708145 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2223. Min Act: -0.0001

Data Index: 216731 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2149. Min Act: -0.0001

Data Index: 687419 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2296. Min Act: -0.0001

Data Index: 179928 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2018. Min Act: -0.0001

Data Index: 884259 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2083. Min Act: -0.0001

Data Index: 414078 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2063. Min Act: -0.0001

Data Index: 445778 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.1989. Min Act: -0.0001

Data Index: 370660 (C4 (Web Text))

Max Activating Token Index: 857