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

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

Neuron 770 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: 0.0464. Min Range: -0.0464

Max Act: 0.0398. Min Act: -0.0006

Data Index: 542350 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1196272 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0444. Min Act: -0.0006

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0391. Min Act: -0.0006

Data Index: 41254 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0390. Min Act: -0.0006

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0442. Min Act: -0.0006

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1172991 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0402. Min Act: -0.0006

Data Index: 444579 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0006

Data Index: 199857 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0442. Min Act: -0.0006

Data Index: 154877 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0396. Min Act: -0.0006

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1126061 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0443. Min Act: -0.0006

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0403. Min Act: -0.0006

Data Index: 1262117 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1321429 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1325531 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0375. Min Act: -0.0006

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0375. Min Act: -0.0006

Data Index: 777285 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0398. Min Act: -0.0006

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0397. Min Act: -0.0006

Data Index: 423138 (C4 (Web Text))

Max Activating Token Index: 967