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

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

Neuron 3681 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1234220 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0597. Min Act: -0.0002

Data Index: 342475 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0505. Min Act: -0.0002

Data Index: 947001 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0460. Min Act: -0.0002

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0430. Min Act: -0.0002

Data Index: 67176 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0396. Min Act: -0.0002

Data Index: 976742 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0425. Min Act: -0.0002

Data Index: 6291 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0435. Min Act: -0.0002

Data Index: 894444 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0399. Min Act: -0.0002

Data Index: 525427 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0415. Min Act: -0.0002

Data Index: 761916 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0378. Min Act: -0.0002

Data Index: 184329 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0384. Min Act: -0.0002

Data Index: 11091 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1265774 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0382. Min Act: -0.0002

Data Index: 756528 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1485646 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0346. Min Act: -0.0002

Data Index: 164627 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0357. Min Act: -0.0002

Data Index: 713603 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0374. Min Act: -0.0002

Data Index: 773197 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1466126 (Python Code)

Max Activating Token Index: 825