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

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

Neuron 978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1494381 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0874. Min Act: -0.0000

Data Index: 408326 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1599655 (Python Code)

Max Activating Token Index: 682

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1595201 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1188221 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0772. Min Act: -0.0000

Data Index: 561576 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1373479 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1485413 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1132238 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1611979 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1642911 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1595555 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1586976 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1122560 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1624034 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1294541 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0583. Min Act: -0.0000

Data Index: 415144 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1415998 (Python Code)

Max Activating Token Index: 473

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1551492 (Python Code)

Max Activating Token Index: 821

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1643843 (Python Code)

Max Activating Token Index: 705