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

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

Neuron 391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0121. Min Range: -2.0121

Max Act: 2.0121. Min Act: -0.0000

Data Index: 95855 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.8784. Min Act: -0.0000

Data Index: 383460 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.6817. Min Act: -0.0000

Data Index: 868128 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.6791. Min Act: -0.0000

Data Index: 908055 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.5905. Min Act: -0.0000

Data Index: 856429 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.7680. Min Act: -0.0000

Data Index: 1378159 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4781. Min Act: -0.0000

Data Index: 1495453 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4829. Min Act: -0.0000

Data Index: 217041 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1530421 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1655987 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1454252 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1501517 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3994. Min Act: -0.0000

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3202. Min Act: -0.0000

Data Index: 86105 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1364881 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4431. Min Act: -0.0000

Data Index: 926455 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3885. Min Act: -0.0000

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1610827 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.5108. Min Act: -0.0000

Data Index: 728600 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 2.0121. Min Range: -2.0121

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1599838 (Python Code)

Max Activating Token Index: 699