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

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

Neuron 1705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1808. Min Act: -0.0001

Data Index: 411060 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2714. Min Act: -0.0001

Data Index: 138726 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2261. Min Act: -0.0001

Data Index: 1130464 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2154. Min Act: -0.0001

Data Index: 746949 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2857. Min Act: -0.0001

Data Index: 23755 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2559. Min Act: -0.0001

Data Index: 143956 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1779. Min Act: -0.0001

Data Index: 1086990 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0276. Min Act: -0.0001

Data Index: 604198 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1721. Min Act: -0.0001

Data Index: 184694 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1514. Min Act: -0.0001

Data Index: 959614 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0778. Min Act: -0.0001

Data Index: 306878 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0533. Min Act: -0.0001

Data Index: 808764 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1375. Min Act: -0.0001

Data Index: 211953 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1564. Min Act: -0.0001

Data Index: 698389 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1667. Min Act: -0.0001

Data Index: 1104007 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1365. Min Act: -0.0001

Data Index: 96644 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0879. Min Act: -0.0001

Data Index: 702232 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.9687. Min Act: -0.0001

Data Index: 571919 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8975. Min Act: -0.0001

Data Index: 315772 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0858. Min Act: -0.0001

Data Index: 271453 (C4 (Web Text))

Max Activating Token Index: 185