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

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

Neuron 780 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5784. Min Range: -2.5784

Max Act: 2.5784. Min Act: -0.0000

Data Index: 724047 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.9928. Min Act: -0.0000

Data Index: 1132197 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.9597. Min Act: -0.0000

Data Index: 2820 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8841. Min Act: -0.0000

Data Index: 444406 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8320. Min Act: -0.0000

Data Index: 34088 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.9802. Min Act: -0.0000

Data Index: 796986 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.7952. Min Act: -0.0000

Data Index: 739189 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.7791. Min Act: -0.0000

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8543. Min Act: -0.0000

Data Index: 133845 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8238. Min Act: -0.0000

Data Index: 602087 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8296. Min Act: -0.0000

Data Index: 1262837 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8890. Min Act: -0.0000

Data Index: 676368 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8083. Min Act: -0.0000

Data Index: 1278105 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8773. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8129. Min Act: -0.0000

Data Index: 538806 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.6882. Min Act: -0.0000

Data Index: 1161080 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.6029. Min Act: -0.0000

Data Index: 426493 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.6872. Min Act: -0.0000

Data Index: 756412 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.8879. Min Act: -0.0000

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.5784. Min Range: -2.5784

Max Act: 1.5905. Min Act: -0.0000

Data Index: 393287 (C4 (Web Text))

Max Activating Token Index: 702