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

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

Neuron 4190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0115. Min Range: -1.0115

Max Act: 1.0115. Min Act: -0.0000

Data Index: 540916 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7105. Min Act: -0.0000

Data Index: 195945 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9011. Min Act: -0.0000

Data Index: 302938 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1302933 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1241759 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7683. Min Act: -0.0000

Data Index: 865172 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7761. Min Act: -0.0000

Data Index: 345322 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7907. Min Act: -0.0000

Data Index: 281342 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7950. Min Act: -0.0000

Data Index: 562505 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7503. Min Act: -0.0000

Data Index: 980266 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1006323 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7176. Min Act: -0.0000

Data Index: 636941 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6674. Min Act: -0.0000

Data Index: 984896 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1228762 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1089714 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6806. Min Act: -0.0000

Data Index: 759466 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1318599 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1108124 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6789. Min Act: -0.0000

Data Index: 916938 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6635. Min Act: -0.0000

Data Index: 386984 (C4 (Web Text))

Max Activating Token Index: 784