Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4235 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.8521. Min Act: -0.0000

Data Index: 382755 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.2198. Min Act: -0.0000

Data Index: 1070884 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.2300. Min Act: -0.0000

Data Index: 1462826 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.8838. Min Act: -0.0000

Data Index: 721472 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.9897. Min Act: -0.0000

Data Index: 859307 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.9702. Min Act: -0.0000

Data Index: 1358721 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.9346. Min Act: -0.0000

Data Index: 415178 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.7795. Min Act: -0.0000

Data Index: 643000 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.6577. Min Act: -0.0000

Data Index: 1549636 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.5744. Min Act: -0.0000

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.5514. Min Act: -0.0000

Data Index: 198258 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.5285. Min Act: -0.0000

Data Index: 420068 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.3458. Min Act: -0.0000

Data Index: 1436618 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1499970 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.3117. Min Act: -0.0000

Data Index: 818511 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.4479. Min Act: -0.0000

Data Index: 459581 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.5305. Min Act: -0.0000

Data Index: 1197828 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.3795. Min Act: -0.0000

Data Index: 184212 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.4972. Min Act: -0.0000

Data Index: 728896 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 3.8521. Min Range: -3.8521

Max Act: 2.3622. Min Act: -0.0000

Data Index: 1473785 (Python Code)

Max Activating Token Index: 42