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

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

Neuron 600 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: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0003

Data Index: 970774 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1151428 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0830. Min Act: -0.0002

Data Index: 431122 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0749. Min Act: -0.0003

Data Index: 968831 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1358193 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1300171 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0737. Min Act: -0.0003

Data Index: 290934 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1009647 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0685. Min Act: -0.0003

Data Index: 518343 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0702. Min Act: -0.0002

Data Index: 514284 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1276569 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0691. Min Act: -0.0003

Data Index: 587002 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0674. Min Act: -0.0002

Data Index: 566191 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0697. Min Act: -0.0002

Data Index: 904125 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1287394 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0654. Min Act: -0.0003

Data Index: 47077 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0641. Min Act: -0.0002

Data Index: 283159 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0656. Min Act: -0.0003

Data Index: 495993 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1232063 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0638. Min Act: -0.0002

Data Index: 476700 (C4 (Web Text))

Max Activating Token Index: 538