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

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

Neuron 1110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.1140. Min Act: -0.0000

Data Index: 301790 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.2406. Min Act: -0.0000

Data Index: 40405 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0937. Min Act: -0.0000

Data Index: 872269 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0833. Min Act: -0.0000

Data Index: 642019 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.3170. Min Act: -0.0000

Data Index: 429662 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.1628. Min Act: -0.0000

Data Index: 700336 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9764. Min Act: -0.0000

Data Index: 255400 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9706. Min Act: -0.0000

Data Index: 1348691 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.2478. Min Act: -0.0000

Data Index: 406957 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.8887. Min Act: -0.0000

Data Index: 1135500 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9417. Min Act: -0.0000

Data Index: 966977 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9586. Min Act: -0.0000

Data Index: 857370 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0634. Min Act: -0.0000

Data Index: 1083444 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0777. Min Act: -0.0000

Data Index: 1270411 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9253. Min Act: -0.0000

Data Index: 821111 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.9307. Min Act: -0.0000

Data Index: 1023780 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0702. Min Act: -0.0000

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.0738. Min Act: -0.0000

Data Index: 409270 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.3170. Min Range: -3.3170

Max Act: 3.2017. Min Act: -0.0000

Data Index: 1006115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3170. Min Range: -3.3170

Max Act: 2.7122. Min Act: -0.0000

Data Index: 738753 (C4 (Web Text))

Max Activating Token Index: 1004