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

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

Neuron 4590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.4120. Min Act: -0.0000

Data Index: 813229 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.3054. Min Act: -0.0000

Data Index: 1248567 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.2288. Min Act: -0.0000

Data Index: 100689 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.7429. Min Act: -0.0000

Data Index: 579506 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.7496. Min Act: -0.0000

Data Index: 662964 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.3577. Min Act: -0.0000

Data Index: 1276892 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.4644. Min Act: -0.0000

Data Index: 952981 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.3078. Min Act: -0.0000

Data Index: 349915 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.0009. Min Act: -0.0000

Data Index: 137338 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.2434. Min Act: -0.0000

Data Index: 338259 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.1896. Min Act: -0.0000

Data Index: 457695 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.2738. Min Act: -0.0000

Data Index: 1225818 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.0368. Min Act: -0.0000

Data Index: 857163 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.8826. Min Act: -0.0000

Data Index: 354966 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.8270. Min Act: -0.0000

Data Index: 497936 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.1075. Min Act: -0.0000

Data Index: 82968 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.9369. Min Act: -0.0000

Data Index: 35885 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.7433. Min Act: -0.0000

Data Index: 1101719 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.8752. Min Act: -0.0000

Data Index: 165406 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 4.4120. Min Range: -4.4120

Max Act: 2.8842. Min Act: -0.0000

Data Index: 769256 (C4 (Web Text))

Max Activating Token Index: 190