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

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

Neuron 891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0592. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0896. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.2417. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.9371. Min Act: -0.0000

Data Index: 869572 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.8673. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.8643. Min Act: -0.0000

Data Index: 540708 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.8670. Min Act: -0.0000

Data Index: 244803 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.7105. Min Act: -0.0000

Data Index: 321767 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.4699. Min Act: -0.0000

Data Index: 457069 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.5564. Min Act: -0.0000

Data Index: 43811 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.5915. Min Act: -0.0000

Data Index: 881048 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.1821. Min Act: -0.0000

Data Index: 40942 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.4430. Min Act: -0.0000

Data Index: 472886 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.1677. Min Act: -0.0000

Data Index: 861412 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.3837. Min Act: -0.0000

Data Index: 882589 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.3586. Min Act: -0.0000

Data Index: 560197 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1354627 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.3419. Min Act: -0.0000

Data Index: 413050 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.1104. Min Act: -0.0001

Data Index: 571274 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 4.0896. Min Range: -4.0896

Max Act: 2.4370. Min Act: -0.0000

Data Index: 719180 (C4 (Web Text))

Max Activating Token Index: 689