Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1064 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0002

Data Index: 1016152 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1043902 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1663. Min Act: -0.0002

Data Index: 839639 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1639. Min Act: -0.0002

Data Index: 1354163 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1636. Min Act: -0.0002

Data Index: 673971 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1548. Min Act: -0.0002

Data Index: 962503 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1585. Min Act: -0.0002

Data Index: 857768 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1553. Min Act: -0.0002

Data Index: 416475 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1270214 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1559. Min Act: -0.0002

Data Index: 803981 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1496. Min Act: -0.0002

Data Index: 894078 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1526. Min Act: -0.0002

Data Index: 195812 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1547. Min Act: -0.0002

Data Index: 141749 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1413. Min Act: -0.0002

Data Index: 463823 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1343566 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1536. Min Act: -0.0002

Data Index: 1036941 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1330338 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1470. Min Act: -0.0002

Data Index: 626684 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1411. Min Act: -0.0002

Data Index: 424698 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1231528 (C4 (Web Text))

Max Activating Token Index: 661