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

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

Neuron 2395 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0001

Data Index: 427968 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1848. Min Act: -0.0001

Data Index: 890585 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1829. Min Act: -0.0001

Data Index: 871092 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1166033 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1569. Min Act: -0.0001

Data Index: 803951 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1773. Min Act: -0.0001

Data Index: 930966 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1804. Min Act: -0.0001

Data Index: 500396 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1731. Min Act: -0.0001

Data Index: 414399 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1719. Min Act: -0.0001

Data Index: 288417 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1768. Min Act: -0.0001

Data Index: 680354 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1190671 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1593. Min Act: -0.0001

Data Index: 294526 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1627. Min Act: -0.0001

Data Index: 538524 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1586. Min Act: -0.0001

Data Index: 390571 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1245641 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1620. Min Act: -0.0001

Data Index: 730006 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1507. Min Act: -0.0001

Data Index: 244881 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1205423 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1505. Min Act: -0.0001

Data Index: 774775 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1415. Min Act: -0.0001

Data Index: 851608 (C4 (Web Text))

Max Activating Token Index: 613