Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0000

Data Index: 632698 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4209. Min Act: -0.0000

Data Index: 657814 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4141. Min Act: -0.0000

Data Index: 992115 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4389. Min Act: -0.0001

Data Index: 768904 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4508. Min Act: -0.0000

Data Index: 301572 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1058146 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4315. Min Act: -0.0001

Data Index: 323816 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3992. Min Act: -0.0000

Data Index: 60557 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3971. Min Act: -0.0000

Data Index: 427814 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3741. Min Act: -0.0001

Data Index: 97633 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3855. Min Act: -0.0000

Data Index: 762920 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3716. Min Act: -0.0000

Data Index: 644649 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1030249 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3785. Min Act: -0.0000

Data Index: 882035 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3539. Min Act: -0.0000

Data Index: 737237 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1138744 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3526. Min Act: -0.0000

Data Index: 719835 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3400. Min Act: -0.0000

Data Index: 661966 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3398. Min Act: -0.0000

Data Index: 85100 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3311. Min Act: -0.0001

Data Index: 662866 (C4 (Web Text))

Max Activating Token Index: 216