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

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

Neuron 2795 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0003

Data Index: 1078027 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1623719 (Python Code)

Max Activating Token Index: 433

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1512863 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1490292 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0629. Min Act: -0.0003

Data Index: 30297 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1572434 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0572. Min Act: -0.0003

Data Index: 242755 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1523214 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1038842 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1309037 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1491510 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0548. Min Act: -0.0003

Data Index: 985273 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0524. Min Act: -0.0003

Data Index: 594714 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0519. Min Act: -0.0003

Data Index: 900274 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1631137 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1364417 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0503. Min Act: -0.0003

Data Index: 709 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1323583 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0480. Min Act: -0.0003

Data Index: 495158 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0480. Min Act: -0.0003

Data Index: 152176 (C4 (Web Text))

Max Activating Token Index: 434