Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1547 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.2456. Min Act: -0.0000

Data Index: 750712 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1021574 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.0227. Min Act: -0.0000

Data Index: 249935 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.0058. Min Act: -0.0000

Data Index: 956160 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.0107. Min Act: -0.0000

Data Index: 752345 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9801. Min Act: -0.0000

Data Index: 817198 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9369. Min Act: -0.0000

Data Index: 351231 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1354037 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8449. Min Act: -0.0000

Data Index: 60700 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1300810 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9316. Min Act: -0.0000

Data Index: 240145 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8859. Min Act: -0.0000

Data Index: 968285 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8183. Min Act: -0.0000

Data Index: 662714 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8481. Min Act: -0.0000

Data Index: 572220 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8644. Min Act: -0.0000

Data Index: 934249 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8896. Min Act: -0.0000

Data Index: 997021 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1083532 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1284708 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8629. Min Act: -0.0000

Data Index: 795241 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7755. Min Act: -0.0000

Data Index: 79234 (C4 (Web Text))

Max Activating Token Index: 244