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

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

Neuron 1256 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: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0006

Data Index: 993118 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1126108 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1108011 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0338. Min Act: -0.0006

Data Index: 759814 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0314. Min Act: -0.0007

Data Index: 1272753 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1074166 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1276385 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0305. Min Act: -0.0006

Data Index: 26221 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0006

Data Index: 11964 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0006

Data Index: 620871 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0298. Min Act: -0.0006

Data Index: 231618 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0280. Min Act: -0.0006

Data Index: 500824 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0289. Min Act: -0.0006

Data Index: 672437 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1159514 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0304. Min Act: -0.0006

Data Index: 940601 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1042933 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0271. Min Act: -0.0006

Data Index: 67963 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1188531 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0269. Min Act: -0.0006

Data Index: 165137 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0006

Data Index: 106198 (C4 (Web Text))

Max Activating Token Index: 909