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

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

Neuron 4375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0421. Min Act: -0.0001

Data Index: 461501 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0438. Min Act: -0.0001

Data Index: 933452 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0504. Min Act: -0.0001

Data Index: 7356 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0219. Min Act: -0.0001

Data Index: 609542 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0006. Min Act: -0.0001

Data Index: 411034 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.0504. Min Range: -1.0504

Max Act: 1.0006. Min Act: -0.0001

Data Index: 658375 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9850. Min Act: -0.0001

Data Index: 362272 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9823. Min Act: -0.0001

Data Index: 801702 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9906. Min Act: -0.0001

Data Index: 477010 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9758. Min Act: -0.0001

Data Index: 871314 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9813. Min Act: -0.0001

Data Index: 829825 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1271915 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9959. Min Act: -0.0001

Data Index: 263648 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9731. Min Act: -0.0001

Data Index: 524002 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9666. Min Act: -0.0001

Data Index: 520830 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1340345 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9519. Min Act: -0.0001

Data Index: 563107 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9568. Min Act: -0.0002

Data Index: 553991 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9531. Min Act: -0.0001

Data Index: 167356 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.0504. Min Range: -1.0504

Max Act: 0.9412. Min Act: -0.0001

Data Index: 288881 (C4 (Web Text))

Max Activating Token Index: 571