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

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

Neuron 2392 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: 1.2179. Min Range: -1.2179

Max Act: 1.2179. Min Act: -0.0000

Data Index: 258756 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1389462 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1337966 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9769. Min Act: -0.0000

Data Index: 245837 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0176. Min Act: -0.0000

Data Index: 972363 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1346705 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1034185 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9346. Min Act: -0.0000

Data Index: 438040 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8972. Min Act: -0.0000

Data Index: 712016 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1601597 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8574. Min Act: -0.0000

Data Index: 739377 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8284. Min Act: -0.0000

Data Index: 879797 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8403. Min Act: -0.0000

Data Index: 693228 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8406. Min Act: -0.0000

Data Index: 980699 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8655. Min Act: -0.0000

Data Index: 718225 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8247. Min Act: -0.0000

Data Index: 378495 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1229109 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8238. Min Act: -0.0000

Data Index: 398492 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.7824. Min Act: -0.0000

Data Index: 864374 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8354. Min Act: -0.0000

Data Index: 344040 (C4 (Web Text))

Max Activating Token Index: 761