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

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

Neuron 426 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: 1.1026. Min Range: -1.1026

Max Act: 1.1026. Min Act: -0.0001

Data Index: 349043 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.9013. Min Act: -0.0001

Data Index: 545209 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8620. Min Act: -0.0001

Data Index: 236532 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.9116. Min Act: -0.0001

Data Index: 656989 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.9023. Min Act: -0.0001

Data Index: 802849 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8485. Min Act: -0.0001

Data Index: 845841 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8705. Min Act: -0.0001

Data Index: 48612 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8121. Min Act: -0.0001

Data Index: 714798 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8540. Min Act: -0.0001

Data Index: 328247 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8216. Min Act: -0.0001

Data Index: 839023 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8494. Min Act: -0.0001

Data Index: 635470 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8145. Min Act: -0.0001

Data Index: 973396 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8586. Min Act: -0.0001

Data Index: 832231 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7582. Min Act: -0.0001

Data Index: 863940 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8341. Min Act: -0.0001

Data Index: 908278 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7783. Min Act: -0.0001

Data Index: 378464 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7499. Min Act: -0.0001

Data Index: 311333 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7662. Min Act: -0.0001

Data Index: 612748 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8311. Min Act: -0.0001

Data Index: 774827 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7732. Min Act: -0.0001

Data Index: 197817 (C4 (Web Text))

Max Activating Token Index: 246