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

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

Neuron 3086 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9105. Min Act: -0.0001

Data Index: 1010313 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9545. Min Act: -0.0001

Data Index: 607471 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8308. Min Act: -0.0001

Data Index: 932026 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8815. Min Act: -0.0001

Data Index: 575441 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8526. Min Act: -0.0001

Data Index: 394970 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1289578 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1267982 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1105347 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7141. Min Act: -0.0001

Data Index: 882466 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6748. Min Act: -0.0001

Data Index: 1001973 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6659. Min Act: -0.0001

Data Index: 204152 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7305. Min Act: -0.0001

Data Index: 743723 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6683. Min Act: -0.0001

Data Index: 1082557 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1100589 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6608. Min Act: -0.0001

Data Index: 614180 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6594. Min Act: -0.0001

Data Index: 116927 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6891. Min Act: -0.0001

Data Index: 1200365 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6757. Min Act: -0.0001

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6749. Min Act: -0.0001

Data Index: 938327 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6322. Min Act: -0.0001

Data Index: 65268 (C4 (Web Text))

Max Activating Token Index: 372