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

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

Neuron 1701 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: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1272519 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0780. Min Act: -0.0001

Data Index: 598148 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1261786 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0689. Min Act: -0.0001

Data Index: 522338 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1068869 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0651. Min Act: -0.0001

Data Index: 187947 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1249926 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0657. Min Act: -0.0001

Data Index: 265122 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0611. Min Act: -0.0001

Data Index: 703784 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0610. Min Act: -0.0001

Data Index: 608499 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0621. Min Act: -0.0001

Data Index: 656014 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0619. Min Act: -0.0001

Data Index: 253764 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0602. Min Act: -0.0001

Data Index: 428363 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0595. Min Act: -0.0001

Data Index: 9533 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0585. Min Act: -0.0001

Data Index: 973840 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0578. Min Act: -0.0001

Data Index: 215777 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0598. Min Act: -0.0001

Data Index: 784593 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0599. Min Act: -0.0001

Data Index: 123630 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0001

Data Index: 432287 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0588. Min Act: -0.0001

Data Index: 266879 (C4 (Web Text))

Max Activating Token Index: 679