Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0005

Data Index: 78025 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1778. Min Act: -0.0005

Data Index: 903308 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1692. Min Act: -0.0005

Data Index: 34088 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1681. Min Act: -0.0005

Data Index: 518511 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1632. Min Act: -0.0005

Data Index: 1114818 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1589. Min Act: -0.0005

Data Index: 1190096 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1632. Min Act: -0.0005

Data Index: 346029 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1510. Min Act: -0.0005

Data Index: 1306508 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1507. Min Act: -0.0005

Data Index: 332501 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1470. Min Act: -0.0005

Data Index: 1022521 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1466. Min Act: -0.0005

Data Index: 1308110 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1506. Min Act: -0.0005

Data Index: 107532 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1502. Min Act: -0.0005

Data Index: 137491 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1449. Min Act: -0.0005

Data Index: 1357169 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1440. Min Act: -0.0005

Data Index: 774679 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1535. Min Act: -0.0005

Data Index: 557182 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1434. Min Act: -0.0005

Data Index: 116848 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1434. Min Act: -0.0005

Data Index: 714814 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1461. Min Act: -0.0005

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1405. Min Act: -0.0005

Data Index: 709826 (C4 (Web Text))

Max Activating Token Index: 195