Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1097364 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0585. Min Act: -0.0000

Data Index: 108590 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0625. Min Act: -0.0000

Data Index: 393378 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1535017 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0626. Min Act: -0.0000

Data Index: 521447 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1323268 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1011123 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0579. Min Act: -0.0000

Data Index: 801394 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0576. Min Act: -0.0000

Data Index: 701494 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0543. Min Act: -0.0000

Data Index: 374144 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1078309 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0508. Min Act: -0.0000

Data Index: 446413 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0520. Min Act: -0.0000

Data Index: 26961 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1320236 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1586764 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1516168 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1605963 (Python Code)

Max Activating Token Index: 230

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0511. Min Act: -0.0000

Data Index: 427225 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1161002 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0552. Min Act: -0.0000

Data Index: 633325 (C4 (Web Text))

Max Activating Token Index: 184