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

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

Neuron 1580 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: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0006

Data Index: 386284 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0353. Min Act: -0.0006

Data Index: 700614 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0345. Min Act: -0.0006

Data Index: 712807 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0352. Min Act: -0.0006

Data Index: 34891 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0346. Min Act: -0.0006

Data Index: 240596 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0338. Min Act: -0.0006

Data Index: 545097 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0337. Min Act: -0.0006

Data Index: 483740 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1300693 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0332. Min Act: -0.0006

Data Index: 1051592 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0337. Min Act: -0.0006

Data Index: 896539 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0336. Min Act: -0.0006

Data Index: 903377 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0006

Data Index: 967424 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0321. Min Act: -0.0006

Data Index: 645760 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0326. Min Act: -0.0006

Data Index: 70920 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1008378 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0314. Min Act: -0.0006

Data Index: 314672 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0307. Min Act: -0.0006

Data Index: 1180485 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0307. Min Act: -0.0006

Data Index: 607216 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0314. Min Act: -0.0006

Data Index: 643136 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0313. Min Act: -0.0006

Data Index: 878039 (C4 (Web Text))

Max Activating Token Index: 769