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

Dataset: The Pile

Neuron 720 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.7728. Min Act: -0.0000

Data Index: 1686470 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 7.5214. Min Range: -7.5214

Max Act: 7.2464. Min Act: -0.0000

Data Index: 540814 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.5765. Min Act: -0.0000

Data Index: 1078164 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 7.5214. Min Range: -7.5214

Max Act: 7.5214. Min Act: -0.0000

Data Index: 1299480 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.4012. Min Act: -0.0000

Data Index: 1057265 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 7.5214. Min Range: -7.5214

Max Act: 7.0688. Min Act: -0.0000

Data Index: 277680 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.7782. Min Act: -0.0000

Data Index: 703939 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.0036. Min Act: -0.0000

Data Index: 836180 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.2604. Min Act: -0.0000

Data Index: 514176 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.0071. Min Act: -0.0000

Data Index: 1700583 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 7.5214. Min Range: -7.5214

Max Act: 5.9573. Min Act: -0.0000

Data Index: 1450981 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.1496. Min Act: -0.0000

Data Index: 1597009 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.1548. Min Act: -0.0000

Data Index: 759612 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.0581. Min Act: -0.0000

Data Index: 1293108 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 7.5214. Min Range: -7.5214

Max Act: 6.2325. Min Act: -0.0000

Data Index: 311071 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 7.5214. Min Range: -7.5214

Max Act: 5.5359. Min Act: -0.0000

Data Index: 1009548 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 7.5214. Min Range: -7.5214

Max Act: 5.4731. Min Act: -0.0000

Data Index: 1736695 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 7.5214. Min Range: -7.5214

Max Act: 5.6151. Min Act: -0.0000

Data Index: 718380 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 7.5214. Min Range: -7.5214

Max Act: 4.9908. Min Act: -0.0000

Data Index: 853660 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 7.5214. Min Range: -7.5214

Max Act: 5.8648. Min Act: -0.0000

Data Index: 776350 (The Pile)

Max Activating Token Index: 444