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

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

Neuron 3368 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.9061. Min Act: -0.0001

Data Index: 175466 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.8410. Min Act: -0.0001

Data Index: 1595406 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.7459. Min Act: -0.0001

Data Index: 1380826 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.8087. Min Act: -0.0001

Data Index: 1476033 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.6679. Min Act: -0.0001

Data Index: 831093 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5445. Min Act: -0.0001

Data Index: 1071412 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.7087. Min Act: -0.0001

Data Index: 553027 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5032. Min Act: -0.0001

Data Index: 1637605 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.6167. Min Act: -0.0001

Data Index: 898418 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.6096. Min Act: -0.0001

Data Index: 1401623 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5858. Min Act: -0.0001

Data Index: 1526689 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.6343. Min Act: -0.0001

Data Index: 1471644 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5520. Min Act: -0.0001

Data Index: 1384644 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5520. Min Act: -0.0001

Data Index: 1574872 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5520. Min Act: -0.0001

Data Index: 1366066 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5520. Min Act: -0.0001

Data Index: 1525277 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5520. Min Act: -0.0001

Data Index: 1409640 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.5274. Min Act: -0.0001

Data Index: 1495431 (Python Code)

Max Activating Token Index: 714

Text #18

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.4525. Min Act: -0.0001

Data Index: 1558265 (Python Code)

Max Activating Token Index: 611

Text #19

Max Range: 1.9061. Min Range: -1.9061

Max Act: 1.4494. Min Act: -0.0001

Data Index: 1488199 (Python Code)

Max Activating Token Index: 521