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

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

Neuron 433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2472. Min Act: -0.0001

Data Index: 502045 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.3145. Min Act: -0.0001

Data Index: 835720 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.2510. Min Act: -0.0001

Data Index: 1431036 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.3027. Min Act: -0.0001

Data Index: 553674 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1741. Min Act: -0.0001

Data Index: 1553767 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1571. Min Act: -0.0001

Data Index: 824144 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0281. Min Act: -0.0001

Data Index: 888060 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0862. Min Act: -0.0001

Data Index: 357061 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0569. Min Act: -0.0001

Data Index: 271491 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1440159 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9838. Min Act: -0.0001

Data Index: 488862 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0538. Min Act: -0.0001

Data Index: 652249 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9473. Min Act: -0.0001

Data Index: 927556 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9777. Min Act: -0.0001

Data Index: 780126 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9515. Min Act: -0.0001

Data Index: 555216 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9164. Min Act: -0.0001

Data Index: 1299024 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9847. Min Act: -0.0001

Data Index: 64556 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.3145. Min Range: -1.3145

Max Act: 1.0317. Min Act: -0.0001

Data Index: 1355826 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1285520 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.3145. Min Range: -1.3145

Max Act: 0.9774. Min Act: -0.0001

Data Index: 818664 (C4 (Web Text))

Max Activating Token Index: 399