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

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

Neuron 24 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8540. Min Act: -0.0001

Data Index: 114431 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7622. Min Act: -0.0001

Data Index: 133105 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7700. Min Act: -0.0001

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7163. Min Act: -0.0001

Data Index: 375401 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7443. Min Act: -0.0001

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1169831 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6609. Min Act: -0.0001

Data Index: 386342 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6171. Min Act: -0.0001

Data Index: 170059 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6246. Min Act: -0.0001

Data Index: 829011 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1172960 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1238879 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6418. Min Act: -0.0001

Data Index: 1167348 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5588. Min Act: -0.0001

Data Index: 488781 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5714. Min Act: -0.0001

Data Index: 295990 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5639. Min Act: -0.0001

Data Index: 263920 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5689. Min Act: -0.0001

Data Index: 909788 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5330. Min Act: -0.0001

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1340616 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.5802. Min Act: -0.0001

Data Index: 933567 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6013. Min Act: -0.0001

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 941