Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.2462. Min Act: -0.0002

Data Index: 465818 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0320. Min Act: -0.0002

Data Index: 1019703 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0200. Min Act: -0.0002

Data Index: 1001535 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9685. Min Act: -0.0002

Data Index: 818146 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9625. Min Act: -0.0002

Data Index: 687494 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9540. Min Act: -0.0002

Data Index: 180425 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9706. Min Act: -0.0002

Data Index: 99298 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9575. Min Act: -0.0002

Data Index: 8434 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9970. Min Act: -0.0002

Data Index: 211334 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9219. Min Act: -0.0002

Data Index: 224963 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8710. Min Act: -0.0002

Data Index: 361523 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9657. Min Act: -0.0002

Data Index: 208938 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9610. Min Act: -0.0002

Data Index: 905716 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9342. Min Act: -0.0002

Data Index: 455595 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9548. Min Act: -0.0002

Data Index: 103834 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8807. Min Act: -0.0002

Data Index: 1103426 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8951. Min Act: -0.0002

Data Index: 38930 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8897. Min Act: -0.0002

Data Index: 993622 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8854. Min Act: -0.0002

Data Index: 679548 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8840. Min Act: -0.0002

Data Index: 104841 (C4 (Web Text))

Max Activating Token Index: 860