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

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

Neuron 2866 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: 0.3389. Min Range: -0.3389

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1565899 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1631083 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1031081 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1637147 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1476658 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1513495 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1559450 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1483951 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1572806 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1208841 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1408980 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1585053 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1379868 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1587601 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1628245 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1422478 (Python Code)

Max Activating Token Index: 1001

Text #16

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1486066 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1453484 (Python Code)

Max Activating Token Index: 813

Text #18

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1422268 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1368713 (Python Code)

Max Activating Token Index: 699