Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1095 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0466. Min Act: -0.0006

Data Index: 870401 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0006

Data Index: 887276 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0453. Min Act: -0.0006

Data Index: 464946 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0462. Min Act: -0.0006

Data Index: 715533 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0439. Min Act: -0.0006

Data Index: 989602 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0429. Min Act: -0.0006

Data Index: 205228 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0421. Min Act: -0.0006

Data Index: 1198706 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0428. Min Act: -0.0006

Data Index: 683538 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0401. Min Act: -0.0006

Data Index: 812570 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0382. Min Act: -0.0006

Data Index: 937257 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1011955 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0375. Min Act: -0.0006

Data Index: 101905 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1301105 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1002926 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1203775 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1163060 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0366. Min Act: -0.0006

Data Index: 488722 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0365. Min Act: -0.0006

Data Index: 148129 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0374. Min Act: -0.0006

Data Index: 54041 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0364. Min Act: -0.0006

Data Index: 409834 (C4 (Web Text))

Max Activating Token Index: 994