Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1261444 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0001

Data Index: 925383 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0350. Min Act: -0.0001

Data Index: 41178 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1077963 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1147748 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0343. Min Act: -0.0001

Data Index: 761869 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0328. Min Act: -0.0001

Data Index: 344698 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1896 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0335. Min Act: -0.0002

Data Index: 908274 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0350. Min Act: -0.0002

Data Index: 847805 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0347. Min Act: -0.0001

Data Index: 24365 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0335. Min Act: -0.0002

Data Index: 716066 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1321484 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0360. Min Act: -0.0001

Data Index: 554647 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0341. Min Act: -0.0002

Data Index: 794070 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0332. Min Act: -0.0002

Data Index: 369568 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0340. Min Act: -0.0002

Data Index: 827639 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0321. Min Act: -0.0001

Data Index: 881522 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1224458 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0328. Min Act: -0.0002

Data Index: 431297 (C4 (Web Text))

Max Activating Token Index: 187