Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2547 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2855. Min Act: -0.0002

Data Index: 1395843 (Python Code)

Max Activating Token Index: 293

Text #1

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2781. Min Act: -0.0002

Data Index: 1448579 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2783. Min Act: -0.0002

Data Index: 1552943 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2766. Min Act: -0.0002

Data Index: 1432780 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2741. Min Act: -0.0003

Data Index: 100996 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2696. Min Act: -0.0002

Data Index: 1460018 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2640. Min Act: -0.0002

Data Index: 1612935 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2636. Min Act: -0.0002

Data Index: 1639750 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2724. Min Act: -0.0002

Data Index: 1465037 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2614. Min Act: -0.0002

Data Index: 1527893 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2602. Min Act: -0.0002

Data Index: 1500193 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2600. Min Act: -0.0002

Data Index: 1655703 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2597. Min Act: -0.0002

Data Index: 1413206 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2577. Min Act: -0.0002

Data Index: 1373831 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2572. Min Act: -0.0002

Data Index: 1600423 (Python Code)

Max Activating Token Index: 913

Text #15

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2563. Min Act: -0.0003

Data Index: 246359 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2609. Min Act: -0.0002

Data Index: 1361518 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2510. Min Act: -0.0002

Data Index: 1455505 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2418. Min Act: -0.0002

Data Index: 1511157 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2412. Min Act: -0.0002

Data Index: 1606597 (Python Code)

Max Activating Token Index: 325