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

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

Neuron 4790 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.8281. Min Act: -0.0000

Data Index: 1082663 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.4121. Min Act: -0.0000

Data Index: 51738 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1067256 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.0628. Min Act: -0.0001

Data Index: 425622 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.2294. Min Act: -0.0001

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.1711. Min Act: -0.0000

Data Index: 928349 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.1609. Min Act: -0.0000

Data Index: 922623 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.3379. Min Act: -0.0001

Data Index: 518642 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.0843. Min Act: -0.0000

Data Index: 699451 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.1701. Min Act: -0.0000

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8037. Min Act: -0.0000

Data Index: 219369 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8987. Min Act: -0.0000

Data Index: 728794 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8934. Min Act: -0.0001

Data Index: 1299281 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1075154 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8623. Min Act: -0.0000

Data Index: 901978 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.8271. Min Act: -0.0000

Data Index: 213074 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.7435. Min Act: -0.0000

Data Index: 494932 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.7049. Min Act: -0.0000

Data Index: 574582 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 2.8281. Min Range: -2.8281

Max Act: 1.7698. Min Act: -0.0000

Data Index: 723369 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 2.8281. Min Range: -2.8281

Max Act: 2.0439. Min Act: -0.0000

Data Index: 925655 (C4 (Web Text))

Max Activating Token Index: 392