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

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

Neuron 2104 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: 0.4775. Min Range: -0.4775

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1472866 (Python Code)

Max Activating Token Index: 919

Text #1

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1434540 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1369366 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1619351 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1563146 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1609561 (Python Code)

Max Activating Token Index: 990

Text #6

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1417448 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1582188 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1498507 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1427107 (Python Code)

Max Activating Token Index: 847

Text #10

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1586531 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1567235 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1558864 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1575807 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1464246 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1593525 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1537001 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1524613 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1375211 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1477185 (Python Code)

Max Activating Token Index: 275