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

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

Neuron 3729 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1105796 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8819. Min Act: -0.0000

Data Index: 785495 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1280165 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8582. Min Act: -0.0000

Data Index: 175811 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8579. Min Act: -0.0000

Data Index: 669582 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8821. Min Act: -0.0000

Data Index: 909767 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7184. Min Act: -0.0000

Data Index: 6473 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1255136 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6853. Min Act: -0.0000

Data Index: 454286 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6963. Min Act: -0.0000

Data Index: 676214 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6415. Min Act: -0.0000

Data Index: 151709 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6795. Min Act: -0.0000

Data Index: 167150 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1225001 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1578412 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6013. Min Act: -0.0000

Data Index: 785420 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1108356 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1054791 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.5720. Min Act: -0.0000

Data Index: 839210 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.5699. Min Act: -0.0000

Data Index: 213032 (C4 (Web Text))

Max Activating Token Index: 677