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

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

Neuron 1824 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: 1.9987. Min Range: -1.9987

Max Act: 1.8728. Min Act: -0.0001

Data Index: 1544289 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.8623. Min Act: -0.0001

Data Index: 1364612 (Python Code)

Max Activating Token Index: 198

Text #2

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.9652. Min Act: -0.0001

Data Index: 1434477 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.7809. Min Act: -0.0001

Data Index: 1415495 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.9091. Min Act: -0.0001

Data Index: 1413971 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.9987. Min Act: -0.0001

Data Index: 1504322 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.8229. Min Act: -0.0001

Data Index: 1443638 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.6594. Min Act: -0.0001

Data Index: 1529084 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5360. Min Act: -0.0001

Data Index: 1400207 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.6907. Min Act: -0.0001

Data Index: 1600702 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.6554. Min Act: -0.0001

Data Index: 1510909 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.7292. Min Act: -0.0001

Data Index: 1644105 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5549. Min Act: -0.0001

Data Index: 1626723 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.7130. Min Act: -0.0001

Data Index: 1495288 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5637. Min Act: -0.0001

Data Index: 1561396 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.6139. Min Act: -0.0001

Data Index: 1522011 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5932. Min Act: -0.0001

Data Index: 1368593 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.4007. Min Act: -0.0001

Data Index: 1579577 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.4731. Min Act: -0.0001

Data Index: 1572482 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5603. Min Act: -0.0001

Data Index: 1419262 (Python Code)

Max Activating Token Index: 15