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

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

Neuron 4352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.4569. Min Act: -0.0000

Data Index: 117407 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3842. Min Act: -0.0000

Data Index: 661530 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3361. Min Act: -0.0000

Data Index: 273969 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3459. Min Act: -0.0000

Data Index: 73611 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3388. Min Act: -0.0000

Data Index: 445404 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3469. Min Act: -0.0000

Data Index: 568475 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3053. Min Act: -0.0000

Data Index: 33444 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1382701 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2907. Min Act: -0.0000

Data Index: 126407 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2876. Min Act: -0.0000

Data Index: 135157 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1178598 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1059218 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2778. Min Act: -0.0000

Data Index: 901692 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2661. Min Act: -0.0000

Data Index: 732118 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1144187 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2728. Min Act: -0.0000

Data Index: 660585 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2714. Min Act: -0.0000

Data Index: 618679 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2689. Min Act: -0.0000

Data Index: 138373 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2670. Min Act: -0.0000

Data Index: 275706 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1163631 (C4 (Web Text))

Max Activating Token Index: 884