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

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

Neuron 953 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1497559 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7833. Min Act: -0.0001

Data Index: 1545032 (Python Code)

Max Activating Token Index: 349

Text #2

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1500236 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1505949 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7219. Min Act: -0.0001

Data Index: 1615001 (Python Code)

Max Activating Token Index: 201

Text #5

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1380886 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1620705 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1515983 (Python Code)

Max Activating Token Index: 434

Text #8

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7951. Min Act: -0.0001

Data Index: 1407226 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7020. Min Act: -0.0001

Data Index: 1459994 (Python Code)

Max Activating Token Index: 513

Text #10

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1652129 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1383375 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1415555 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1645635 (Python Code)

Max Activating Token Index: 78

Text #14

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1429584 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1652429 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1508622 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1595899 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1581652 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.7951. Min Range: -0.7951

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1580443 (Python Code)

Max Activating Token Index: 347