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

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

Neuron 197 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3907. Min Act: -0.0000

Data Index: 871506 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3789. Min Act: -0.0000

Data Index: 312320 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3805. Min Act: -0.0000

Data Index: 200882 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0000

Data Index: 800695 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3810. Min Act: -0.0000

Data Index: 488854 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3889. Min Act: -0.0000

Data Index: 622344 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1241648 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3486. Min Act: -0.0000

Data Index: 645831 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1195354 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3375. Min Act: -0.0000

Data Index: 547639 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3312. Min Act: -0.0000

Data Index: 38313 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3504. Min Act: -0.0000

Data Index: 175193 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1277020 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3016. Min Act: -0.0000

Data Index: 830603 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3004. Min Act: -0.0000

Data Index: 679244 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1213073 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2656. Min Act: -0.0000

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2481. Min Act: -0.0000

Data Index: 297354 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2453. Min Act: -0.0000

Data Index: 695151 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2711. Min Act: -0.0000

Data Index: 621673 (C4 (Web Text))

Max Activating Token Index: 467