Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3182 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7307. Min Act: -0.0003

Data Index: 1631538 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7159. Min Act: -0.0003

Data Index: 1224800 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7129. Min Act: -0.0003

Data Index: 683237 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6702. Min Act: -0.0004

Data Index: 1171133 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7056. Min Act: -0.0003

Data Index: 199761 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7252. Min Act: -0.0003

Data Index: 603110 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7461. Min Act: -0.0003

Data Index: 333737 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7689. Min Act: -0.0003

Data Index: 1085889 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7633. Min Act: -0.0003

Data Index: 246813 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5727. Min Act: -0.0003

Data Index: 67921 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6861. Min Act: -0.0003

Data Index: 1108288 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6495. Min Act: -0.0003

Data Index: 1023123 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6405. Min Act: -0.0003

Data Index: 861794 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6958. Min Act: -0.0003

Data Index: 930624 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6861. Min Act: -0.0003

Data Index: 1292804 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7019. Min Act: -0.0003

Data Index: 499582 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6403. Min Act: -0.0003

Data Index: 422570 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5239. Min Act: -0.0003

Data Index: 1344824 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6168. Min Act: -0.0003

Data Index: 730048 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6569. Min Act: -0.0003

Data Index: 885352 (C4 (Web Text))

Max Activating Token Index: 1013