Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3741 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.3587. Min Act: -0.0000

Data Index: 1578204 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.5373. Min Act: 0.0000

Data Index: 1491734 (Python Code)

Max Activating Token Index: 479

Text #2

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1548170 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.2659. Min Act: -0.0000

Data Index: 1615064 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.0704. Min Act: -0.0000

Data Index: 1651174 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.1339. Min Act: -0.0000

Data Index: 1394823 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8612. Min Act: 0.0000

Data Index: 1585936 (Python Code)

Max Activating Token Index: 335

Text #7

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1557270 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 3.3587. Min Range: -3.3587

Max Act: 2.0087. Min Act: 0.0000

Data Index: 1516761 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8842. Min Act: 0.0000

Data Index: 1543814 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8537. Min Act: -0.0000

Data Index: 1541702 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8735. Min Act: -0.0000

Data Index: 1443609 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1587687 (Python Code)

Max Activating Token Index: 241

Text #13

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1368552 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1474693 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1408398 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1385193 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.7389. Min Act: -0.0000

Data Index: 1583603 (Python Code)

Max Activating Token Index: 539

Text #18

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.8660. Min Act: -0.0000

Data Index: 1587530 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 3.3587. Min Range: -3.3587

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1652611 (Python Code)

Max Activating Token Index: 576