Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1490 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1079985 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0340. Min Act: -0.0004

Data Index: 1287920 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0352. Min Act: -0.0004

Data Index: 405560 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0353. Min Act: -0.0004

Data Index: 490175 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0353. Min Act: -0.0004

Data Index: 58976 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0351. Min Act: -0.0004

Data Index: 775928 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0004

Data Index: 305018 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1341514 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0342. Min Act: -0.0004

Data Index: 327695 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0337. Min Act: -0.0004

Data Index: 72357 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1169414 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1264420 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0329. Min Act: -0.0004

Data Index: 717606 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0004

Data Index: 843231 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0282. Min Act: -0.0004

Data Index: 647905 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0317. Min Act: -0.0004

Data Index: 354800 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0285. Min Act: -0.0004

Data Index: 123834 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1035483 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1095107 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1357510 (C4 (Web Text))

Max Activating Token Index: 74