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

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

Neuron 296 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: 2.0707. Min Range: -2.0707

Max Act: 2.0707. Min Act: -0.0002

Data Index: 789260 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.0707. Min Range: -2.0707

Max Act: 2.0597. Min Act: -0.0002

Data Index: 588484 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.9824. Min Act: -0.0002

Data Index: 197676 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.0707. Min Range: -2.0707

Max Act: 2.0101. Min Act: -0.0002

Data Index: 1131589 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.9628. Min Act: -0.0002

Data Index: 838256 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.8532. Min Act: -0.0002

Data Index: 106657 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.8409. Min Act: -0.0002

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.8445. Min Act: -0.0002

Data Index: 494448 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7882. Min Act: -0.0002

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.8256. Min Act: -0.0002

Data Index: 1249395 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7702. Min Act: -0.0002

Data Index: 940446 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7430. Min Act: -0.0002

Data Index: 436908 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7351. Min Act: -0.0002

Data Index: 534997 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7332. Min Act: -0.0002

Data Index: 1323513 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7533. Min Act: -0.0002

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.6677. Min Act: -0.0002

Data Index: 648074 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.7421. Min Act: -0.0002

Data Index: 555959 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.6926. Min Act: -0.0002

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.6535. Min Act: -0.0002

Data Index: 309436 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 2.0707. Min Range: -2.0707

Max Act: 1.6747. Min Act: -0.0002

Data Index: 819741 (C4 (Web Text))

Max Activating Token Index: 23