Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.7312. Min Act: -0.0003

Data Index: 412775 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6991. Min Act: -0.0002

Data Index: 737733 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.7078. Min Act: -0.0002

Data Index: 701743 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6771. Min Act: -0.0003

Data Index: 1100151 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6961. Min Act: -0.0003

Data Index: 842246 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6476. Min Act: -0.0002

Data Index: 763267 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6702. Min Act: -0.0003

Data Index: 1210963 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6656. Min Act: -0.0003

Data Index: 305729 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6963. Min Act: -0.0003

Data Index: 295489 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6689. Min Act: -0.0003

Data Index: 554948 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6365. Min Act: -0.0003

Data Index: 802751 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6626. Min Act: -0.0003

Data Index: 482568 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6344. Min Act: -0.0003

Data Index: 1144272 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6535. Min Act: -0.0003

Data Index: 18718 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6578. Min Act: -0.0003

Data Index: 603746 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6471. Min Act: -0.0002

Data Index: 564420 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6449. Min Act: -0.0003

Data Index: 874189 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6450. Min Act: -0.0003

Data Index: 183823 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6224. Min Act: -0.0003

Data Index: 494440 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6357. Min Act: -0.0002

Data Index: 1292 (C4 (Web Text))

Max Activating Token Index: 581