Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3811 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2399. Min Act: -0.0001

Data Index: 473233 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2178. Min Act: -0.0001

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1874. Min Act: -0.0001

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1754. Min Act: -0.0001

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1574661 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1699. Min Act: -0.0001

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1608. Min Act: -0.0001

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1374822 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1531. Min Act: -0.0001

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1549. Min Act: -0.0001

Data Index: 623206 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1033068 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1583527 (Python Code)

Max Activating Token Index: 289

Text #12

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1544348 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1513887 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1395727 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1585554 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1580947 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1365415 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1437. Min Act: -0.0001

Data Index: 136931 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1237156 (C4 (Web Text))

Max Activating Token Index: 956