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

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

Neuron 444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.5557. Min Act: -0.0000

Data Index: 16811 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.5061. Min Act: -0.0000

Data Index: 615565 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.4423. Min Act: -0.0000

Data Index: 999726 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1142993 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.4125. Min Act: -0.0000

Data Index: 757664 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3916. Min Act: -0.0000

Data Index: 96195 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3918. Min Act: -0.0000

Data Index: 861236 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1074979 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1246571 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.4035. Min Act: -0.0000

Data Index: 961100 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3804. Min Act: -0.0000

Data Index: 139543 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3645. Min Act: -0.0000

Data Index: 610203 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3522. Min Act: -0.0000

Data Index: 729318 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3587. Min Act: -0.0000

Data Index: 66782 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1382386 (Python Code)

Max Activating Token Index: 879

Text #15

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3598. Min Act: -0.0000

Data Index: 318551 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3700. Min Act: -0.0000

Data Index: 123925 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3576. Min Act: -0.0000

Data Index: 282346 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3563. Min Act: -0.0000

Data Index: 683578 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.5557. Min Range: -0.5557

Max Act: 0.3530. Min Act: -0.0000

Data Index: 708682 (C4 (Web Text))

Max Activating Token Index: 702