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

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

Neuron 2864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.3841. Min Act: -0.0000

Data Index: 355046 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.0778. Min Act: -0.0000

Data Index: 209195 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.1638. Min Act: -0.0000

Data Index: 1272299 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.1482. Min Act: -0.0000

Data Index: 839787 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.2200. Min Act: -0.0000

Data Index: 568110 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1153421 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.9096. Min Act: -0.0000

Data Index: 87234 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.0112. Min Act: -0.0000

Data Index: 1135321 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8764. Min Act: -0.0000

Data Index: 671841 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8353. Min Act: -0.0000

Data Index: 1084825 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 2.3841. Min Range: -2.3841

Max Act: 2.0656. Min Act: -0.0000

Data Index: 635533 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8305. Min Act: -0.0000

Data Index: 618865 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.9144. Min Act: -0.0000

Data Index: 585091 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.7961. Min Act: -0.0000

Data Index: 646125 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.7755. Min Act: -0.0000

Data Index: 311500 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8694. Min Act: -0.0000

Data Index: 233170 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1214867 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8451. Min Act: -0.0000

Data Index: 502448 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8431. Min Act: -0.0000

Data Index: 895518 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 2.3841. Min Range: -2.3841

Max Act: 1.8333. Min Act: -0.0000

Data Index: 788201 (C4 (Web Text))

Max Activating Token Index: 64