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

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

Neuron 342 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: 1.5043. Min Range: -1.5043

Max Act: 1.4227. Min Act: -0.0000

Data Index: 25959 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1130341 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1277595 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.4601. Min Act: -0.0000

Data Index: 30531 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1204723 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1252925 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.4017. Min Act: -0.0000

Data Index: 728169 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1306659 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2770. Min Act: -0.0000

Data Index: 982809 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2722. Min Act: -0.0000

Data Index: 166641 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2667. Min Act: -0.0000

Data Index: 127786 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2280. Min Act: -0.0000

Data Index: 529928 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1255545 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3279. Min Act: -0.0000

Data Index: 997619 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3175. Min Act: -0.0000

Data Index: 154924 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2626. Min Act: -0.0000

Data Index: 735219 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.3278. Min Act: -0.0000

Data Index: 745288 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1054263 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2600. Min Act: -0.0000

Data Index: 790383 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2623. Min Act: -0.0000

Data Index: 142944 (C4 (Web Text))

Max Activating Token Index: 1012