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

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

Neuron 5457 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: 0.8121. Min Range: -0.8121

Max Act: 0.8121. Min Act: -0.0001

Data Index: 174243 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7826. Min Act: -0.0001

Data Index: 114784 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7773. Min Act: -0.0001

Data Index: 1111322 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7226. Min Act: -0.0001

Data Index: 473255 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7036. Min Act: -0.0001

Data Index: 630876 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1305786 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1220890 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6656. Min Act: -0.0001

Data Index: 720434 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6783. Min Act: -0.0001

Data Index: 249659 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6604. Min Act: -0.0001

Data Index: 1110676 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6537. Min Act: -0.0001

Data Index: 482184 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6633. Min Act: -0.0001

Data Index: 1172060 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6421. Min Act: -0.0002

Data Index: 79395 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6471. Min Act: -0.0001

Data Index: 171465 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6477. Min Act: -0.0001

Data Index: 84569 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6343. Min Act: -0.0001

Data Index: 785379 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6300. Min Act: -0.0001

Data Index: 579080 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6354. Min Act: -0.0001

Data Index: 19337 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6242. Min Act: -0.0001

Data Index: 856338 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6220. Min Act: -0.0001

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 640