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

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

Neuron 4305 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.5902. Min Act: -0.0001

Data Index: 834034 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.5913. Min Act: -0.0001

Data Index: 100278 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2793. Min Act: -0.0001

Data Index: 1360932 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.6044. Min Act: -0.0001

Data Index: 112079 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.4904. Min Act: -0.0001

Data Index: 727576 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2569. Min Act: -0.0001

Data Index: 1621791 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.3227. Min Act: -0.0001

Data Index: 1595465 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.4427. Min Act: -0.0001

Data Index: 621995 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.4572. Min Act: -0.0001

Data Index: 1141157 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.3407. Min Act: -0.0001

Data Index: 1421734 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.3464. Min Act: -0.0001

Data Index: 694048 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.4756. Min Act: -0.0001

Data Index: 228560 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2429. Min Act: -0.0001

Data Index: 1593453 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.1612. Min Act: -0.0001

Data Index: 1590505 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.3344. Min Act: -0.0001

Data Index: 1556026 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2554. Min Act: -0.0001

Data Index: 415190 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1614632 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.1963. Min Act: -0.0001

Data Index: 1378216 (Python Code)

Max Activating Token Index: 743

Text #18

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.4642. Min Act: -0.0001

Data Index: 1451605 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 1.6044. Min Range: -1.6044

Max Act: 1.1963. Min Act: -0.0001

Data Index: 1397778 (Python Code)

Max Activating Token Index: 399