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

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

Neuron 3263 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.6536. Min Act: -0.0000

Data Index: 387866 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.6153. Min Act: 0.0000

Data Index: 1214063 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1359583 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1278702 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3577. Min Act: -0.0000

Data Index: 409661 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.4327. Min Act: -0.0000

Data Index: 108875 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1115579 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3211. Min Act: -0.0000

Data Index: 772586 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3844. Min Act: 0.0000

Data Index: 1133099 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.2962. Min Act: -0.0000

Data Index: 960173 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3658. Min Act: -0.0000

Data Index: 15795 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3550. Min Act: -0.0000

Data Index: 558825 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3489. Min Act: -0.0000

Data Index: 76571 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3408. Min Act: -0.0000

Data Index: 881699 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.2535. Min Act: -0.0000

Data Index: 451759 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3243. Min Act: -0.0000

Data Index: 625085 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1136090 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3095. Min Act: -0.0000

Data Index: 749783 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3114. Min Act: -0.0000

Data Index: 172190 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 1.6536. Min Range: -1.6536

Max Act: 1.3691. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 950