Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3334 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1272707 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1289185 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.2371. Min Act: -0.0000

Data Index: 832765 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.2770. Min Act: -0.0000

Data Index: 317959 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1257818 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0734. Min Act: -0.0000

Data Index: 310794 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1526. Min Act: -0.0000

Data Index: 781184 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1300. Min Act: -0.0000

Data Index: 931640 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1455. Min Act: -0.0000

Data Index: 528231 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1327. Min Act: -0.0000

Data Index: 256629 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1138. Min Act: -0.0000

Data Index: 73513 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1099. Min Act: 0.0000

Data Index: 1018697 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0758. Min Act: -0.0000

Data Index: 837071 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0704. Min Act: -0.0000

Data Index: 351920 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0041. Min Act: -0.0000

Data Index: 233974 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1244512 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.0707. Min Act: -0.0000

Data Index: 505458 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1314. Min Act: -0.0000

Data Index: 75681 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1223. Min Act: -0.0000

Data Index: 770537 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 1.3701. Min Range: -1.3701

Max Act: 1.1209. Min Act: -0.0000

Data Index: 901838 (C4 (Web Text))

Max Activating Token Index: 866