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

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

Neuron 1356 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4817. Min Act: -0.0001

Data Index: 353669 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4949. Min Act: -0.0000

Data Index: 500717 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4854. Min Act: -0.0000

Data Index: 21623 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4676. Min Act: -0.0001

Data Index: 5126 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4835. Min Act: -0.0000

Data Index: 256194 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4738. Min Act: -0.0001

Data Index: 378145 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4727. Min Act: -0.0000

Data Index: 545006 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4477. Min Act: -0.0000

Data Index: 501641 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4584. Min Act: -0.0000

Data Index: 492197 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4562. Min Act: -0.0001

Data Index: 483470 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4420. Min Act: -0.0000

Data Index: 706462 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4382. Min Act: -0.0000

Data Index: 219459 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1096048 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4128. Min Act: -0.0001

Data Index: 182694 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4536. Min Act: -0.0001

Data Index: 976060 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4475. Min Act: -0.0000

Data Index: 841511 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1277242 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4015. Min Act: -0.0000

Data Index: 620681 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1215064 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1093770 (C4 (Web Text))

Max Activating Token Index: 718