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

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

Neuron 2048 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.6148. Min Act: -0.0001

Data Index: 465662 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.3890. Min Act: -0.0001

Data Index: 63384 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.1876. Min Act: -0.0001

Data Index: 777530 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.0506. Min Act: -0.0001

Data Index: 954704 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.1662. Min Act: -0.0001

Data Index: 456697 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7393. Min Act: -0.0001

Data Index: 897677 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.6148. Min Range: -1.6148

Max Act: 1.0957. Min Act: -0.0001

Data Index: 786057 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.9117. Min Act: -0.0001

Data Index: 228837 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7761. Min Act: -0.0001

Data Index: 355124 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1279445 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.8357. Min Act: -0.0001

Data Index: 525659 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7880. Min Act: -0.0001

Data Index: 948823 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.8203. Min Act: -0.0001

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7516. Min Act: -0.0001

Data Index: 4342 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.6323. Min Act: -0.0001

Data Index: 483684 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1353716 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7859. Min Act: -0.0001

Data Index: 445505 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.7642. Min Act: -0.0001

Data Index: 892636 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.5993. Min Act: -0.0001

Data Index: 561504 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.6148. Min Range: -1.6148

Max Act: 0.6822. Min Act: -0.0001

Data Index: 867656 (C4 (Web Text))

Max Activating Token Index: 543