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

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

Neuron 4714 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: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0002

Data Index: 822361 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0665. Min Act: -0.0001

Data Index: 114996 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0634. Min Act: -0.0001

Data Index: 958950 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0583. Min Act: -0.0001

Data Index: 802670 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0590. Min Act: -0.0001

Data Index: 983225 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0580. Min Act: -0.0001

Data Index: 669756 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0581. Min Act: -0.0001

Data Index: 394780 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0571. Min Act: -0.0001

Data Index: 811457 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0582. Min Act: -0.0001

Data Index: 162942 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0554. Min Act: -0.0001

Data Index: 529467 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0562. Min Act: -0.0001

Data Index: 62669 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1280397 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0556. Min Act: -0.0001

Data Index: 86765 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0531. Min Act: -0.0001

Data Index: 583668 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1426216 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0547. Min Act: -0.0001

Data Index: 279268 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1098343 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0521. Min Act: -0.0001

Data Index: 410595 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1327866 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1625959 (Python Code)

Max Activating Token Index: 703