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

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

Neuron 273 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: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0006

Data Index: 874672 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0387. Min Act: -0.0006

Data Index: 130064 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0384. Min Act: -0.0006

Data Index: 932252 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0354. Min Act: -0.0006

Data Index: 185326 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0347. Min Act: -0.0006

Data Index: 430041 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0350. Min Act: -0.0006

Data Index: 563441 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0342. Min Act: -0.0006

Data Index: 322092 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0328. Min Act: -0.0006

Data Index: 788684 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0353. Min Act: -0.0006

Data Index: 69989 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1045232 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0334. Min Act: -0.0006

Data Index: 593464 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0350. Min Act: -0.0006

Data Index: 297976 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0357. Min Act: -0.0006

Data Index: 924076 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0322. Min Act: -0.0006

Data Index: 17624 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0343. Min Act: -0.0006

Data Index: 683323 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0348. Min Act: -0.0006

Data Index: 523813 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0323. Min Act: -0.0006

Data Index: 221995 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1311287 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0339. Min Act: -0.0006

Data Index: 973329 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1321552 (C4 (Web Text))

Max Activating Token Index: 28