Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1392 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1170569 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.4786. Min Act: -0.0000

Data Index: 832309 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.5504. Min Act: -0.0000

Data Index: 364083 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.4294. Min Act: -0.0000

Data Index: 640956 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.3777. Min Act: -0.0000

Data Index: 245461 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.3570. Min Act: -0.0000

Data Index: 829110 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.3277. Min Act: -0.0000

Data Index: 69348 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2774. Min Act: -0.0000

Data Index: 285682 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2716. Min Act: -0.0000

Data Index: 259685 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2733. Min Act: -0.0000

Data Index: 915305 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2614. Min Act: -0.0000

Data Index: 682330 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1051496 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2628. Min Act: -0.0000

Data Index: 113008 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1069482 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2445. Min Act: -0.0000

Data Index: 552781 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1109795 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2380. Min Act: -0.0000

Data Index: 635243 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1098303 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.1938. Min Act: -0.0000

Data Index: 33902 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.7523. Min Range: -1.7523

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1316964 (C4 (Web Text))

Max Activating Token Index: 185