Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3751. Min Act: -0.0001

Data Index: 862580 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3801. Min Act: -0.0001

Data Index: 982342 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3657. Min Act: -0.0001

Data Index: 927365 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3741. Min Act: -0.0001

Data Index: 898657 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3553. Min Act: -0.0001

Data Index: 450274 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3691. Min Act: -0.0001

Data Index: 1017777 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3506. Min Act: -0.0001

Data Index: 74489 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3493. Min Act: -0.0001

Data Index: 526367 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3480. Min Act: -0.0001

Data Index: 10365 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3476. Min Act: -0.0001

Data Index: 140363 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3449. Min Act: -0.0001

Data Index: 594413 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3430. Min Act: -0.0001

Data Index: 232196 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3412. Min Act: -0.0001

Data Index: 17225 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3144. Min Act: -0.0001

Data Index: 593375 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3269. Min Act: -0.0001

Data Index: 499871 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3369. Min Act: -0.0001

Data Index: 534160 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1042580 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1014434 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3205. Min Act: -0.0001

Data Index: 721698 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3419. Min Act: -0.0001

Data Index: 925229 (C4 (Web Text))

Max Activating Token Index: 199