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

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

Neuron 2183 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1604067 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1504735 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8551. Min Act: 0.0000

Data Index: 1513660 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1547392 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1529184 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1610895 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1528035 (Python Code)

Max Activating Token Index: 510

Text #7

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1364933 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1547962 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7831. Min Act: -0.0001

Data Index: 1411316 (Python Code)

Max Activating Token Index: 712

Text #10

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8049. Min Act: 0.0000

Data Index: 1653506 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1511705 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1381636 (Python Code)

Max Activating Token Index: 881

Text #13

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1421713 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1628452 (Python Code)

Max Activating Token Index: 653

Text #15

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1623602 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1531537 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1651655 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1499142 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1480655 (Python Code)

Max Activating Token Index: 864