Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1173320 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1963. Min Act: -0.0001

Data Index: 874435 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2148. Min Act: -0.0001

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1191851 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1540717 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1735. Min Act: -0.0001

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1679. Min Act: -0.0001

Data Index: 382571 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1233508 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1773. Min Act: -0.0001

Data Index: 430363 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1530. Min Act: -0.0001

Data Index: 967911 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1745. Min Act: -0.0001

Data Index: 479503 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1508954 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1664. Min Act: -0.0001

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1604. Min Act: -0.0001

Data Index: 620928 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1088555 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1617983 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1571. Min Act: -0.0001

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1535. Min Act: -0.0001

Data Index: 754073 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1556. Min Act: -0.0001

Data Index: 155068 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1543438 (Python Code)

Max Activating Token Index: 555