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

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

Neuron 542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1422533 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1634935 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1472108 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7682. Min Act: -0.0001

Data Index: 1562772 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7419. Min Act: -0.0001

Data Index: 1475596 (Python Code)

Max Activating Token Index: 538

Text #5

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1645551 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1517159 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1360662 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1422084 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1480039 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1553111 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1593729 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6501. Min Act: -0.0001

Data Index: 1615552 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1627665 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1511315 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1386759 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1365688 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6320. Min Act: -0.0001

Data Index: 1436686 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1627635 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6117. Min Act: -0.0001

Data Index: 1615968 (Python Code)

Max Activating Token Index: 1011