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

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

Neuron 4939 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.9150. Min Act: -0.0000

Data Index: 226148 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1132049 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1167475 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.7790. Min Act: -0.0000

Data Index: 881658 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6716. Min Act: -0.0000

Data Index: 690346 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6797. Min Act: -0.0000

Data Index: 762899 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6632. Min Act: -0.0000

Data Index: 218779 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6401. Min Act: -0.0000

Data Index: 593718 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5987. Min Act: -0.0000

Data Index: 852783 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6237. Min Act: -0.0000

Data Index: 817063 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5831. Min Act: -0.0000

Data Index: 599420 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5907. Min Act: -0.0000

Data Index: 176031 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5700. Min Act: -0.0000

Data Index: 673743 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5916. Min Act: -0.0000

Data Index: 277299 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5787. Min Act: -0.0000

Data Index: 390857 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5247. Min Act: -0.0000

Data Index: 596328 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1150682 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5343. Min Act: -0.0000

Data Index: 103944 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5467. Min Act: -0.0000

Data Index: 552436 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5242. Min Act: -0.0000

Data Index: 91021 (C4 (Web Text))

Max Activating Token Index: 956