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

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

Neuron 4862 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.7735. Min Act: -0.0000

Data Index: 282824 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.6222. Min Act: -0.0000

Data Index: 1133830 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.4376. Min Act: -0.0000

Data Index: 421292 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.4197. Min Act: -0.0000

Data Index: 164110 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.2890. Min Act: -0.0000

Data Index: 1101134 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.1133. Min Act: -0.0000

Data Index: 633704 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0686. Min Act: -0.0000

Data Index: 81414 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.2576. Min Act: -0.0000

Data Index: 926161 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0487. Min Act: -0.0000

Data Index: 405411 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.2247. Min Act: -0.0000

Data Index: 663162 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.1442. Min Act: -0.0000

Data Index: 752757 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 5.7735. Min Range: -5.7735

Max Act: 4.7587. Min Act: -0.0000

Data Index: 704473 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0961. Min Act: -0.0000

Data Index: 19265 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0966. Min Act: -0.0000

Data Index: 407890 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.7735. Min Range: -5.7735

Max Act: 4.9032. Min Act: -0.0000

Data Index: 1276064 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0378. Min Act: -0.0000

Data Index: 334690 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0316. Min Act: -0.0000

Data Index: 1129780 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0339. Min Act: -0.0000

Data Index: 526719 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.0295. Min Act: -0.0000

Data Index: 46531 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 5.7735. Min Range: -5.7735

Max Act: 5.2201. Min Act: -0.0000

Data Index: 481098 (C4 (Web Text))

Max Activating Token Index: 156