Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1180268 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0854. Min Act: -0.0001

Data Index: 878115 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0687. Min Act: -0.0001

Data Index: 845255 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1083001 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0612. Min Act: -0.0001

Data Index: 801233 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1037060 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0557. Min Act: 0.0000

Data Index: 179745 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0640. Min Act: -0.0001

Data Index: 742139 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1098957 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0505. Min Act: -0.0001

Data Index: 632659 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1023582 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0517. Min Act: -0.0001

Data Index: 323099 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0484. Min Act: -0.0001

Data Index: 362602 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0469. Min Act: -0.0001

Data Index: 813244 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1167183 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1079640 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0558. Min Act: -0.0001

Data Index: 308871 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0521. Min Act: -0.0001

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1140391 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1290740 (C4 (Web Text))

Max Activating Token Index: 476