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

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

Neuron 679 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8006. Min Range: -4.8006

Max Act: 4.8006. Min Act: -0.0002

Data Index: 188895 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.7998. Min Act: -0.0001

Data Index: 1341581 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.5620. Min Act: -0.0002

Data Index: 396692 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.4965. Min Act: -0.0001

Data Index: 1048334 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.3393. Min Act: -0.0002

Data Index: 1083019 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.4459. Min Act: -0.0002

Data Index: 71144 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.3802. Min Act: -0.0002

Data Index: 1055844 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.1968. Min Act: -0.0001

Data Index: 981460 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.1603. Min Act: -0.0002

Data Index: 563991 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.1452. Min Act: -0.0002

Data Index: 366448 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.1259. Min Act: -0.0002

Data Index: 576033 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.1140. Min Act: -0.0002

Data Index: 732516 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.0946. Min Act: -0.0002

Data Index: 913438 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.0172. Min Act: -0.0002

Data Index: 1024518 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.0075. Min Act: -0.0002

Data Index: 260631 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 4.8006. Min Range: -4.8006

Max Act: 3.0025. Min Act: -0.0001

Data Index: 889871 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 4.8006. Min Range: -4.8006

Max Act: 2.9990. Min Act: -0.0002

Data Index: 365156 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 4.8006. Min Range: -4.8006

Max Act: 2.9841. Min Act: -0.0002

Data Index: 261892 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 4.8006. Min Range: -4.8006

Max Act: 2.9533. Min Act: -0.0002

Data Index: 1151431 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 4.8006. Min Range: -4.8006

Max Act: 2.9441. Min Act: -0.0002

Data Index: 323319 (C4 (Web Text))

Max Activating Token Index: 756