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

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

Neuron 779 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1165143 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4822. Min Act: -0.0000

Data Index: 629735 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4982. Min Act: -0.0000

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2893. Min Act: -0.0000

Data Index: 836312 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1518230 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1509919 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1168048 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1423109 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1454334 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1373223 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1608612 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2528. Min Act: -0.0000

Data Index: 993636 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1480957 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1361962 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2443. Min Act: -0.0000

Data Index: 767511 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1589860 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2386. Min Act: 0.0000

Data Index: 474858 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2452. Min Act: -0.0000

Data Index: 57937 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2433. Min Act: -0.0000

Data Index: 662853 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1179174 (C4 (Web Text))

Max Activating Token Index: 15