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

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

Neuron 947 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: 1.6707. Min Range: -1.6707

Max Act: 1.6707. Min Act: -0.0002

Data Index: 1114672 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.6000. Min Act: -0.0002

Data Index: 1262408 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.6266. Min Act: -0.0002

Data Index: 555642 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3928. Min Act: -0.0002

Data Index: 1383370 (Python Code)

Max Activating Token Index: 703

Text #4

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3605. Min Act: -0.0002

Data Index: 1311413 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3481. Min Act: -0.0002

Data Index: 767530 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3990. Min Act: -0.0002

Data Index: 968772 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3868. Min Act: -0.0002

Data Index: 447252 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3030. Min Act: -0.0002

Data Index: 464778 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3237. Min Act: -0.0002

Data Index: 205882 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3337. Min Act: -0.0002

Data Index: 348445 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3253. Min Act: -0.0003

Data Index: 954796 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2731. Min Act: -0.0002

Data Index: 527915 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3046. Min Act: -0.0002

Data Index: 752676 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2968. Min Act: -0.0002

Data Index: 341292 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2897. Min Act: -0.0002

Data Index: 294443 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2945. Min Act: -0.0002

Data Index: 1625485 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2250. Min Act: -0.0002

Data Index: 1624682 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2738. Min Act: -0.0002

Data Index: 1574503 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.2265. Min Act: -0.0002

Data Index: 1567970 (Python Code)

Max Activating Token Index: 780