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

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

Neuron 4682 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: 0.1803. Min Range: -0.1803

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1003869 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1799. Min Act: -0.0001

Data Index: 509762 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1768. Min Act: -0.0002

Data Index: 897679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1741. Min Act: -0.0001

Data Index: 962750 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1670. Min Act: -0.0001

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1679. Min Act: -0.0001

Data Index: 115113 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1671. Min Act: -0.0001

Data Index: 773144 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1649. Min Act: -0.0001

Data Index: 51304 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1671. Min Act: -0.0001

Data Index: 511212 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1353274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1057728 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1077727 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1660. Min Act: -0.0001

Data Index: 133913 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1171269 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1638. Min Act: -0.0001

Data Index: 168195 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1619. Min Act: -0.0002

Data Index: 999853 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1253326 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1627. Min Act: -0.0001

Data Index: 498615 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1214880 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1575. Min Act: -0.0001

Data Index: 614109 (C4 (Web Text))

Max Activating Token Index: 320