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

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

Neuron 6098 in Layer 1

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: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 422217 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0578. Min Act: -0.0002

Data Index: 999079 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1035571 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1171038 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0577. Min Act: -0.0002

Data Index: 723867 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0560. Min Act: -0.0002

Data Index: 565646 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1114545 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0555. Min Act: -0.0002

Data Index: 128530 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1105891 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0559. Min Act: -0.0002

Data Index: 154920 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0553. Min Act: -0.0002

Data Index: 228882 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0557. Min Act: -0.0002

Data Index: 841270 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1107130 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1127796 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0549. Min Act: -0.0002

Data Index: 903355 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0557. Min Act: -0.0002

Data Index: 318364 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0543. Min Act: -0.0002

Data Index: 440571 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0551. Min Act: -0.0002

Data Index: 559319 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0554. Min Act: -0.0002

Data Index: 742610 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0540. Min Act: -0.0002

Data Index: 684615 (C4 (Web Text))

Max Activating Token Index: 146