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

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

Neuron 159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1474843 (Python Code)

Max Activating Token Index: 330

Text #1

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1630828 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1460875 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1406564 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1401486 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3433. Min Act: -0.0001

Data Index: 669701 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1446702 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1003386 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.2681. Min Act: -0.0001

Data Index: 1303203 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1385926 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1654279 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1030063 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1605809 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1499145 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1892. Min Act: -0.0001

Data Index: 887547 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1027426 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1496023 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1852. Min Act: -0.0001

Data Index: 667647 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1494270 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1488403 (Python Code)

Max Activating Token Index: 625